BlackOps Center is an MCP server published by io.github.BlackOpsCenter, hosted at mcp.blackopscenter.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 28 tools, including get_me, get_brand_voice, get_recent_notes, get_note, get_ai_context.
Ask your BlackOps brain, capture notes, draft posts, and run your Sorties from any MCP client.
38 connections through 5 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Get current user profile, accessible sites, and account info. Call this first to discover which sites you can manage.
No parameters.
{
"name": "get_me",
"title": "Get Me",
"description": "Get current user profile, accessible sites, and account info. Call this first to discover which sites you can manage.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Get canonical brand voice for the site. Pass domain or site_id to target a specific site; omit to use the auth default. Always pass the same domain/site_id used with patch_brand_voice so both tools operate on the same record. Also returns pronoun_mode and approved_facts when set, empty otherwise — the account-aware check_brand_voice guidance.
| Parameter | Type | Description |
|---|---|---|
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
{
"name": "get_brand_voice",
"title": "Get Brand Voice",
"description": "Get canonical brand voice for the site. Pass domain or site_id to target a specific site; omit to use the auth default. Always pass the same domain/site_id used with patch_brand_voice so both tools operate on the same record. Also returns pronoun_mode and approved_facts when set, empty otherwise — the account-aware check_brand_voice guidance.",
"inputSchema": {
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Get recent notes/context for the site. Recommended before creating tweets/posts.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | How many recent notes to return. Defaults to 5, capped at 20. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
{
"name": "get_recent_notes",
"title": "Get Recent Notes",
"description": "Get recent notes/context for the site. Recommended before creating tweets/posts.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 9007199254740991,
"description": "How many recent notes to return. Defaults to 5, capped at 20.",
"exclusiveMinimum": 0
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Get a single note by UUID, slug, or title. Use this to read the full content of individual notes, including brain source notes referenced in a brain manifest. VAULT SYNC STATUS: the response carries a sync block — status is "queued" (commit in flight), "synced" (landed; see file_path + commit_sha), "failed" (see last_error; the sweeper retries), or "none" (no vault target). This is how you confirm a deferred post_notes commit landed; post_notes itself can only report "queued".
| Parameter | Type | Description |
|---|---|---|
| id * | string | Note UUID, slug, or title |
{
"name": "get_note",
"title": "Get Note",
"description": "Get a single note by UUID, slug, or title. Use this to read the full content of individual notes, including brain source notes referenced in a brain manifest. VAULT SYNC STATUS: the response carries a sync block — status is \"queued\" (commit in flight), \"synced\" (landed; see file_path + commit_sha), \"failed\" (see last_error; the sweeper retries), or \"none\" (no vault target). This is how you confirm a deferred post_notes commit landed; post_notes itself can only report \"queued\".",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Note UUID, slug, or title"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Get AI context pack for content generation. Recommended before creating tweets/posts. Also returns default_site (id, domain, and the rule "unless the user names another site, writes go to <domain>") when the account has one.
| Parameter | Type | Description |
|---|---|---|
| query | string | Optional topic hint for the content you are about to write. Accepted for compatibility; the context pack is not filtered by it. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
{
"name": "get_ai_context",
"title": "Get AI Context",
"description": "Get AI context pack for content generation. Recommended before creating tweets/posts. Also returns default_site (id, domain, and the rule \"unless the user names another site, writes go to <domain>\") when the account has one.",
"inputSchema": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional topic hint for the content you are about to write. Accepted for compatibility; the context pack is not filtered by it."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Create a BlackOps note, or update one in place when source_id resolves to a known note. Requires content_markdown (or transcript/conversation). Prefer this over post_notes_write. source_id is the idempotency key (content hash, your own string, or note UUID): repeat calls update instead of forking. Know the note? Use patch_notes. A SLUG_COLLISION warning ("my-note-2") means an intended update forked. Site is OPTIONAL (explicit → account default intake → only site); pass domain/site_id only for a note tied to one site. BRAINS: pass a brain's UUID as brain_id; the server derives site/target/folder and skips auto-routing. Never infer site_id or guess target_id from topic. brain_alignment confirms the compile picks it up. WITHOUT brain_id, a site opted into auto-routing either files the note into a brain's Triage lane (routing.band "auto", filed: true) or saves it unfiled with needs_brain_choice: show its question, up to 3 options (one-line reason each) and the also entries as ONE single-choice question, then call resolve_with with their pick. Never pick a brain yourself. Sites not opted in save unfiled. suggest_brain: true is a separate keyword match (suggested_brain). Unknown TAGS still apply with an UNKNOWN_TAG warning; ask the user before propose_note_tags. VAULT SYNC is deferred: sync is { status: "queued" } and the note IS saved, so do NOT re-call. Confirm a commit with get_note; wait_for_sync: true returns commitSha/filePath inline. override_folder_path bypasses the taxonomy; a brain's source_folder_path still wins. phase/priority/position are Big Board columns (priority High|Medium|Low).
| Parameter | Type | Description |
|---|---|---|
| tags | array | Tags for the note. Tags outside the site vocabulary still apply, with an UNKNOWN_TAG warning. |
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| phase | string | Big Board phase column for the note, free text (max 100 characters). |
| title | string | Note title, up to 200 characters. |
List blog posts for a site. Filter by status (draft, published) with pagination support.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max posts to return. Defaults to 50, capped at 200. |
| cursor | string | Accepted for compatibility; results are not paginated by cursor, so use limit. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| status | string | Only posts with this status, e.g. "draft", "published" or "scheduled". Omit for all. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
{
"name": "get_posts",
"title": "Get Posts",
"description": "List blog posts for a site. Filter by status (draft, published) with pagination support.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 9007199254740991,
"description": "Max posts to return. Defaults to 50, capped at 200.",
"exclusiveMinimum": 0
},
"cursor": {
"type": "string",
"description": "Accepted for compatibility; results are not paginated by cursor, so use limit."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"status": {
"type": "string",
"description": "Only posts with this status, e.g. \"draft\", \"published\" or \"scheduled\". Omit for all."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Create a blog draft. Before calling, fetch get_me + get_brand_voice (+ get_ai_context/get_recent_notes). Site scope is automatic for a single-site account; pass domain or site_id to target one, and an account with several sites is asked to choose rather than guessed at. Do NOT repeat the title in the content body — no leading "# Title" and no first line restating it, or it renders twice, since the title field prints above the content. Start with the intro paragraph or the first ## heading. The response carries links.review_url: that is where a person previews and edits the draft, so hand the user that link, never the admin editor URL or a raw preview URL.
| Parameter | Type | Description |
|---|---|---|
| slug | string | URL slug for the post. Generated from the title when omitted. |
| tags | array | Tags for the post, e.g. ["ai", "nextjs"]. |
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| title * | string | Post title. Printed above the content, so do not repeat it in the body. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| source | string | Optional label for where the post came from, stored on the post. "bookmark" files it as a bookmark (tagged bookmark, never featured). |
| status | string | Post status: "draft" or "published". Publishing needs confirm: true. |
| confirm | boolean |
Fetch a single blog post by slug or UUID, including full content, metadata, and SEO fields. One call — no need to list posts first to resolve a slug.
| Parameter | Type | Description |
|---|---|---|
| id * | string | Post UUID or slug. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
{
"name": "get_post",
"title": "Get Post",
"description": "Fetch a single blog post by slug or UUID, including full content, metadata, and SEO fields. One call — no need to list posts first to resolve a slug.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Post UUID or slug."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}EDIT ONLY — modifies a post in-place. NEVER call for reading; use post_posts to create. Published edits go live immediately. Always pass base_updated_at (from get_post.updated_at); without it a concurrent edit is silently overwritten. Custom styled HTML needs a richembed fenced block; bare block HTML is escaped. Do NOT include the title in the content body. Response has links.review_url for drafts — give that link to the user.
| Parameter | Type | Description |
|---|---|---|
| id * | string | Post UUID or slug to edit. |
| slug | string | New URL slug. |
| tags | array | Replacement tag list. |
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| title | string | New post title. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| status | string | New status, e.g. "draft" or "published". Setting a scheduled post back to "draft" unschedules it. |
| content | string | New post body in Markdown. Replaces the whole body. Do not include the title. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
Publish a draft blog post, making it live on the site. Requires confirm: true. On a 2026-07-28 connection whose client declares form elicitation you may omit it and the user confirms in a dialog; anywhere else, omitting it fails. Publishing a scheduled post publishes it immediately and clears the schedule. Pass override_brand_voice: true to bypass the brand-voice gate when a publish fails that check.
| Parameter | Type | Description |
|---|---|---|
| id * | string | UUID of the draft post to publish. |
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| confirm | boolean | Pass true to confirm this action once the user has approved it. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
| override_brand_voice | boolean | Set true to publish even though the post fails the brand-voice check. Recorded on the post. |
{
"name": "post_posts_by_id_publish",
"title": "Post Posts by ID Publish",
"description": "Publish a draft blog post, making it live on the site. Requires confirm: true. On a 2026-07-28 connection whose client declares form elicitation you may omit it and the user confirms in a dialog; anywhere else, omitting it fails. Publishing a scheduled post publishes it immediately and clears the schedule. Pass override_brand_voice: true to bypass the brand-voice gate when a publish fails that check.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "UUID of the draft post to publish."
},
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"confirm": {
"type": "boolean",
"description": "Pass true to confirm this action once the user has approved it."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
},
"override_brand_voice": {
"type": "boolean",
"description": "Set true to publish even though the post fails the brand-voice check. Recorded on the post."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Schedule a draft blog post for future publishing. Provide a datetime via scheduledFor; the platform publishes the post automatically at that time (checked every 5 minutes). Unschedule by patching status back to "draft"; publish immediately with post_posts_by_id_publish. Requires confirm: true.
| Parameter | Type | Description |
|---|---|---|
| id * | string | UUID of the draft post to schedule. |
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| confirm * | boolean | Pass true to confirm this action once the user has approved it. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
| schedule_at | string | Alias of scheduledFor. |
| scheduledFor | string | When to publish, ISO 8601 with offset (e.g. 2026-11-12T14:00:00-05:00). One of scheduledFor, scheduled_for or schedule_at is required. |
| scheduled_for | string | Alias of scheduledFor. |
Generate (or regenerate) a blog post's hero image, or its OG social card — works the same before and after the post exists. Returns the image inline plus its public URL. The fields below cover prompts, references, style, and the commit:false review flow. Rules that span fields: only the title and subtitle may ever appear on an OG card, because given anything else the generator invents its own tagline; an OG card takes NO references unless you name them, since auto-matching used to put a real face on social cards nobody asked to be in; for target:"og" prompt is the VISUAL DIRECTION and still gets OG framing; to anchor a face, mark the photo as a "headshot" via mark_reference_image first.
| Parameter | Type | Description |
|---|---|---|
| id * | string | Post UUID |
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| style | string | Visual style. Defaults to "modern". |
| commit | boolean | Default true: apply the image to the post immediately. False generates a review CANDIDATE (kind hero-candidate) and leaves the post untouched. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| prompt | string | Image prompt, auto-generated from the post if omitted. For target:"og", layered on the site share_card_style. |
| target | string | "hero" (default) sets featured_image; "og" makes the 1200x630 Open Graph card and sets og_image, leaving the hero untouched. |
Create a tweet draft. Before calling, fetch get_me + get_brand_voice (+ get_ai_context/get_recent_notes) AND call get_x_accounts for the posting account's max_tweet_length — never assume 280, since Premium/verified accounts go up to 25,000. If max_tweet_length is null the limit is unknown: ask the user rather than defaulting to 280. Site scope is automatic for a single-site account; pass domain or site_id to target one, and an account with several sites is asked to choose rather than guessed at. Requires text or thread. To attach an image, upload with upload_media then call attach_media_to_tweet with the asset_id and this tweet's id. Links to user-owned domains get UTM parameters appended at draft time so the traffic shows up in GA4 instead of as Direct; pass your own if you want explicit campaign slugs. When the tweet distributes a known blog post, pass its post_id (UUID, from get_posts) so the /admin/posts Distribution column links the two automatically — no manual backfill.
| Parameter | Type | Description |
|---|---|---|
| text | string | Tweet text for a single tweet. Pass text or thread, not both. |
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| title | string | Internal title for the draft in BlackOps. Defaults to the start of the first tweet. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| thread | array | A thread, in order: [{ text }, ...]. Pass text or thread, not both. |
| post_id | string | UUID of the blog post this tweet distributes (from get_posts), so the two are linked. |
| site_id |
List connected X (Twitter) accounts. Search by username or filter by site. Each account record includes premium (boolean) and max_tweet_length (integer) — ALWAYS read these before drafting tweet content. Premium accounts allow up to 25,000 chars; non-premium are limited to 280. If max_tweet_length is null, treat the limit as unknown and ask the user rather than assuming 280.
| Parameter | Type | Description |
|---|---|---|
| query | string | Alias of username. |
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
| username | string | Filter accounts by text in the username, display name, account id or site. Case-insensitive. Applies when domain and site_id are omitted. |
| account_name | string | Alias of username. |
{
"name": "get_x_accounts",
"title": "Get X Accounts",
"description": "List connected X (Twitter) accounts. Search by username or filter by site. Each account record includes premium (boolean) and max_tweet_length (integer) — ALWAYS read these before drafting tweet content. Premium accounts allow up to 25,000 chars; non-premium are limited to 280. If max_tweet_length is null, treat the limit as unknown and ask the user rather than assuming 280.",
"inputSchema": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Alias of username."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
},
"username": {
"type": "string",
"description": "Filter accounts by text in the username, display name, account id or site. Case-insensitive. Applies when domain and site_id are omitted."
},
"account_name": {
"type": "string",
"description": "Alias of username."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Upload media to the site media library. Three modes: 1. URL mode — pass file_url + filename + content_type. Fetched server-side in one call, no human step. https only, SSRF-guarded on every redirect, capped at 50 MB (images/PDF) or 200 MB (video; bigger video uses the direct-PUT path below). Good for a URL you already have, e.g. from a generation call. 2. Interactive mode — pass nothing (or just domain/label). Returns { url, token, expires_at }: show the URL; the user uploads on the quick-upload page and clicks "Done". For screenshots, recordings or local files, bulk too. filename/alt_text/title apply to the FIRST asset only. 3. Claim mode — pass token (from interactive mode). Returns status="completed" with an assets[] array once the user clicks Done, or "pending" while they are still uploading — poll again. No public URL but your own HTTP client? get_media_upload_url({ domain, filename, content_type }) → { asset_id, upload_url }, PUT your bytes, then finalize_media_upload({ asset_id, domain }). Token only, no browser. Supported: jpeg, png, webp, gif, mp4, webm, quicktime, application/pdf (quick-upload: video to 1 GB, else 50 MB). Video → media_type "video", no thumbnail. PDF → "document" (thumbnail = page one), the only document type; anything else is rejected.
| Parameter | Type | Description |
|---|---|---|
| kind | string | Library category for the asset. Defaults to "mcp-upload". |
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| label | string | Interactive mode: a label shown on the upload page, up to 200 characters. |
| title | string | Title for the asset in the media library. |
| token | string | Token returned by interactive mode. Pass it alone to claim the finished upload (claim mode). |
Agent-direct upload, no human step. 1: get_media_upload_url({ domain, filename, content_type, size_bytes? }) returns { asset_id, upload_url, public_url, expires_in }. 2: HTTP PUT the raw bytes to upload_url with a matching Content-Type. 3: finalize_media_upload({ asset_id, domain }). For bytes with no public URL, or too big for upload_media URL mode (e.g. video over 200 MB). If the PUT fails with a network error (sandboxed or proxied agent), use upload_media interactive mode instead. Allowed: images, mp4/webm/quicktime, pdf, mp3/wav. Max 20 MB images, 50 MB PDF, 1 GB video. URL expires after expires_in seconds.
| Parameter | Type | Description |
|---|---|---|
| kind | string | Library category for the asset. Defaults to "mcp-upload". |
| title | string | Title for the asset in the media library. |
| domain * | string | Site domain whose media library receives the file (e.g. example.com). |
| alt_text | string | Alt text for the asset. |
| filename * | string | File name to store, with extension (e.g. demo.mp4). |
| size_bytes | integer | File size in bytes, if known. |
| content_type * | string | MIME type you will PUT the bytes with, e.g. video/mp4. Must match the upload. |
Finalize a presigned URL media upload. Call after uploading to the upload_url from upload_media, or after PUTting bytes directly to an upload_url minted by get_media_upload_url. Needs only { asset_id, domain } plus the same MCP/API token already on this session — no browser or cookie. Validates the file and processes dimensions/thumbnails — for a PDF that means rasterizing page one into a badged thumbnail. Bytes that are not really a PDF are rejected; a genuine PDF that will not rasterize still finalizes, just without a preview.
| Parameter | Type | Description |
|---|---|---|
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| domain * | string | The same site domain passed to get_media_upload_url. |
| asset_id * | string | asset_id returned by get_media_upload_url. |
{
"name": "finalize_media_upload",
"title": "Finalize Media Upload",
"description": "Finalize a presigned URL media upload. Call after uploading to the upload_url from upload_media, or after PUTting bytes directly to an upload_url minted by get_media_upload_url. Needs only { asset_id, domain } plus the same MCP/API token already on this session — no browser or cookie. Validates the file and processes dimensions/thumbnails — for a PDF that means rasterizing page one into a badged thumbnail. Bytes that are not really a PDF are rejected; a genuine PDF that will not rasterize still finalizes, just without a preview.",
"inputSchema": {
"type": "object",
"required": [
"asset_id",
"domain"
],
"properties": {
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"domain": {
"type": "string",
"minLength": 1,
"description": "The same site domain passed to get_media_upload_url."
},
"asset_id": {
"type": "string",
"minLength": 1,
"description": "asset_id returned by get_media_upload_url."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Get details for a single media asset including URL, dimensions, format, and metadata.
| Parameter | Type | Description |
|---|---|---|
| id * | string | Media asset UUID (from upload_media or list_media). |
| domain * | string | Site domain that owns the asset (e.g. example.com). |
{
"name": "get_media",
"title": "Get Media",
"description": "Get details for a single media asset including URL, dimensions, format, and metadata.",
"inputSchema": {
"type": "object",
"required": [
"id",
"domain"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Media asset UUID (from upload_media or list_media)."
},
"domain": {
"type": "string",
"minLength": 1,
"description": "Site domain that owns the asset (e.g. example.com)."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}List all brains accessible to the authenticated user. Returns each brain's id, name, description, aliases, status, note count, last compiled timestamp, and visibility. Match description and aliases to resolve natural-language references (e.g. "restaurant brain"). Brains are site-agnostic — no domain or site_id needed. Cross-brain retrieval: returns every brain in the account, so an answer about one can draw on another — say so when it does. Private brains are omitted here but stay readable via get_brain by name.
No parameters.
{
"name": "list_brains",
"title": "List Brains",
"description": "List all brains accessible to the authenticated user. Returns each brain's id, name, description, aliases, status, note count, last compiled timestamp, and visibility. Match description and aliases to resolve natural-language references (e.g. \"restaurant brain\"). Brains are site-agnostic — no domain or site_id needed.\n\nCross-brain retrieval: returns every brain in the account, so an answer about one can draw on another — say so when it does. Private brains are omitted here but stay readable via get_brain by name.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Get the compiled knowledge map for a brain: a manifest of source notes with IDs and summaries — call get_note for a note's full content. Site-agnostic. Accepts a UUID, slug, name, or alias; no list_brains lookup needed first (call list_brains for a brain not named in your instructions). status: "pending" means it has never compiled — call update_brain to add the first note. To create a new brain, call create_brain. The response's pending_triage_count is how many items are held out of this compile awaiting a list_triage / promote_triage_item / dismiss_triage_item decision. AMBIGUITY: when a reference matches more than one brain the response is error "ambiguous_brain_ref" with a candidate list and NO brain. Present the candidates to the user and ask which they mean. Do not infer from context, and do not re-call this tool until they answer.
| Parameter | Type | Description |
|---|---|---|
| brain_id | string | Brain UUID |
| brain_name | string | Brain slug, name, or alias — how the user referred to it |
{
"name": "get_brain",
"title": "Get Brain",
"description": "Get the compiled knowledge map for a brain: a manifest of source notes with IDs and summaries — call get_note for a note's full content. Site-agnostic. Accepts a UUID, slug, name, or alias; no list_brains lookup needed first (call list_brains for a brain not named in your instructions). status: \"pending\" means it has never compiled — call update_brain to add the first note. To create a new brain, call create_brain. The response's pending_triage_count is how many items are held out of this compile awaiting a list_triage / promote_triage_item / dismiss_triage_item decision.\n\nAMBIGUITY: when a reference matches more than one brain the response is error \"ambiguous_brain_ref\" with a candidate list and NO brain. Present the candidates to the user and ask which they mean. Do not infer from context, and do not re-call this tool until they answer.",
"inputSchema": {
"type": "object",
"properties": {
"brain_id": {
"type": "string",
"minLength": 1,
"description": "Brain UUID"
},
"brain_name": {
"type": "string",
"minLength": 1,
"description": "Brain slug, name, or alias — how the user referred to it"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Add a new note to a brain; the server resolves storage from the brain record (BlackOps for DB-backed brains, a GitHub commit for vault-backed ones). Use this whenever the user says "update the brain", "add this to the brain", or "log this in the brain". Call list_brains first for the brain_id if you do not have it; create_brain makes a new brain. A DB-backed brain recompiles immediately; a vault-backed one on its next compile. Use post_notes_write (with brain_id) only for control over the filename or path. A brain's sanitize rules may hold a write: follow details.sanitize_hold.
| Parameter | Type | Description |
|---|---|---|
| agent | string | Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>. |
| brain_id * | string | Brain UUID (from list_brains) |
| allow_secrets | boolean | Set true to store content that looks like a credential (API key, token, private key), which is otherwise refused with SECRET_DETECTED. Only when the user asked to store that exact value. |
| note_filename | string | Filename without .md. Defaults from section_title or the date. |
| section_title | string | Title for this note — used as the filename slug (e.g. "Threads Integration") |
| commit_message | string | Git commit message. |
| sanitize_answer | object | Only after a SANITIZE_ANSWER_REQUIRED hold: repeat the same call with { hold_id, decisions: { <rule>: "allow" | "block" } } for each rule the hold lists, as the owner answered. Send "block" for every rule when no one can be asked. |
Get account context including defaults and publishing context for a domain. The default site (the site writes go to when the user names none) is stated by get_account_settings and get_ai_context (default_site).
| Parameter | Type | Description |
|---|---|---|
| domain * | string | Site domain to read account and publishing context for (e.g. example.com). |
{
"name": "get_account_context",
"title": "Get Account Context",
"description": "Get account context including defaults and publishing context for a domain. The default site (the site writes go to when the user names none) is stated by get_account_settings and get_ai_context (default_site).",
"inputSchema": {
"type": "object",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"minLength": 1,
"description": "Site domain to read account and publishing context for (e.g. example.com)."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}List the account's and built-in skills (slug + description). Call at the START of a task: if one matches the ask, fetch it with get_skill and follow it instead of improvising.
| Parameter | Type | Description |
|---|---|---|
| tags | array | Only skills carrying every one of these tags. |
| brain_id | string | Restrict to skills stored in one brain. |
| platform | string | Only skills that support this host (e.g. "claude", "cursor", "grok"). Skills that declare no platforms always match. |
{
"name": "list_skills",
"title": "List Skills",
"description": "List the account's and built-in skills (slug + description). Call at the START of a task: if one matches the ask, fetch it with get_skill and follow it instead of improvising.",
"inputSchema": {
"type": "object",
"properties": {
"tags": {
"type": "array",
"items": {
"type": "string",
"minLength": 1
},
"maxItems": 10,
"description": "Only skills carrying every one of these tags."
},
"brain_id": {
"type": "string",
"format": "uuid",
"description": "Restrict to skills stored in one brain."
},
"platform": {
"type": "string",
"minLength": 1,
"description": "Only skills that support this host (e.g. \"claude\", \"cursor\", \"grok\"). Skills that declare no platforms always match."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Search BlackOps notes and blog posts. Returns id, title, and url per match; pass an id to fetch for the full text. Generated daily notes (note_type "daily", titled "YYYY-MM-DD · {Name}") do not contain the word "daily" in their title — queries containing "daily" automatically include them via a supplementary typed lookup, but for reliable lookup by context name use list_notes with note_type: "daily" and search: "{name}", or list_daily_note_configs to see which contexts exist.
| Parameter | Type | Description |
|---|---|---|
| query * | string | Search terms, matched against titles and bodies. |
| domain | string | Site domain. Defaults to the account default site. |
{
"name": "search",
"title": "Search",
"description": "Search BlackOps notes and blog posts. Returns id, title, and url per match; pass an id to fetch for the full text. Generated daily notes (note_type \"daily\", titled \"YYYY-MM-DD · {Name}\") do not contain the word \"daily\" in their title — queries containing \"daily\" automatically include them via a supplementary typed lookup, but for reliable lookup by context name use list_notes with note_type: \"daily\" and search: \"{name}\", or list_daily_note_configs to see which contexts exist.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"minLength": 1,
"description": "Search terms, matched against titles and bodies."
},
"domain": {
"type": "string",
"minLength": 1,
"description": "Site domain. Defaults to the account default site."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Retrieve the full text of one BlackOps note or blog post by its search id.
| Parameter | Type | Description |
|---|---|---|
| id * | string | Record id from search, e.g. "note:<uuid>". |
{
"name": "fetch",
"title": "Fetch",
"description": "Retrieve the full text of one BlackOps note or blog post by its search id.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Record id from search, e.g. \"note:<uuid>\"."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Discover the rest of the BlackOps tool catalog. This connector surfaces a small default tool set; every other BlackOps capability (pages, video, brains and brain watches, hunts, sorties, LinkedIn/Threads/Medium, GA4/Search Console analytics, and more) is one lookup away. Call with no arguments for the full index of tool names, with query to search, or with names for complete definitions including input_schema. Then invoke any of them with use_tool.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max full definitions returned for a query (default 5). |
| names | array | Exact tool names to fetch full definitions for. |
| query | string | Keyword search over tool names and descriptions (case-insensitive). |
{
"name": "describe_tools",
"title": "Describe Tools",
"description": "Discover the rest of the BlackOps tool catalog. This connector surfaces a small default tool set; every other BlackOps capability (pages, video, brains and brain watches, hunts, sorties, LinkedIn/Threads/Medium, GA4/Search Console analytics, and more) is one lookup away. Call with no arguments for the full index of tool names, with query to search, or with names for complete definitions including input_schema. Then invoke any of them with use_tool.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 10,
"description": "Max full definitions returned for a query (default 5).",
"exclusiveMinimum": 0
},
"names": {
"type": "array",
"items": {
"type": "string",
"minLength": 1
},
"maxItems": 10,
"description": "Exact tool names to fetch full definitions for."
},
"query": {
"type": "string",
"minLength": 1,
"description": "Keyword search over tool names and descriptions (case-insensitive)."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Invoke any BlackOps catalog tool that is not on the default surface, by name. Arguments are validated against the same schema the tool has natively, and the call runs the identical handler with identical permissions — this is dispatch, not a bypass. Look up names and input schemas with describe_tools first.
| Parameter | Type | Description |
|---|---|---|
| args | object | The tool's arguments, matching the input_schema from describe_tools. |
| name * | string | Catalog tool name, exactly as returned by describe_tools. |
{
"name": "use_tool",
"title": "Use Tool",
"description": "Invoke any BlackOps catalog tool that is not on the default surface, by name. Arguments are validated against the same schema the tool has natively, and the call runs the identical handler with identical permissions — this is dispatch, not a bypass. Look up names and input schemas with describe_tools first.",
"inputSchema": {
"type": "object",
"required": [
"name"
],
"properties": {
"args": {
"type": "object",
"properties": {},
"description": "The tool's arguments, matching the input_schema from describe_tools.",
"additionalProperties": {}
},
"name": {
"type": "string",
"minLength": 1,
"description": "Catalog tool name, exactly as returned by describe_tools."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": true
}
}When calling any tool that requires a site (domain or site_id) and the user has not specified which site to use: 1. Call get_me to discover the user's accessible sites. 2. If the user has only ONE site, use it automatically — no need to ask. 3. If the user has MULTIPLE sites, present the list and ask which one to use. Do NOT guess or default. This applies to all write operations: post_tweets, post_tweets_campaign, post_tweets_reply, post_tweets_quote, post_posts, patch_posts_by_id, post_notes, and any other tool requiring domain or site_id. Analytics memory: every GA4 (ga4_*) and Search Console (gsc_*) tool response includes an `analyticsMemory` block — deltas since the last look, plus the open recommendation ledger and recent findings for that site and surface. Use it: comment on what CHANGED, not absolutes, and do NOT re-surface an open recommendation as if it were new (report progress instead). When you finish an analytics discussion, call log_analytics_finding (per site + surface) to record the summary, findings, and recommendations so the next session builds on them. Use get_analytics_memory for the full history. Voice calibration: the highest-signal way to fix a site's brand voice is to have the user restate AI output in their own words. So: (1) when you produce voice-sensitive content (a post, tweet, headline, bio), offer to let the user restate any part in their own words — don't nag on every line, offer once. (2) When the user says the voice is off ("too formal", "sounds like AI", "that's not how I'd say it"), do NOT just guess a rewrite — ask them to restate it in their own words. Either way, when they give you their version, call calibrate_voice with original_text (what you wrote) and rewritten_text (their version). It returns suggested_changes (additive brand-voice rules) plus a voice anchor. Show the user the suggested rules, then apply them with patch_brand_voice (confirm: true) only after they approve. This is how the voice gets sharper over time for every user. Skills: this account stores its own operating procedures as skills, and BlackOps adds built-in ones (such as run-assigned-hunts). At the START of any task, call list_skills (it returns slug + description only, so it is cheap). If one matches what the user asked for, call get_skill with that slug and follow the returned procedure as written instead of improvising your own. Pass format to get the skill in this host's shape — "claude", "cursor", "agents-md", "grok", or "raw". Do not re-derive a procedure a skill already documents. Shared memory (Continuity): the user can give all of their agents one shared, current memory. If you have a Continuity handle saved in your own instructions, follow it: read get_continuity_digest at the start of work, continuity_append decisions, handoffs and open loops as they happen, and call continuity_heartbeat at the start of each piece of work (and before a session ends, if you have hooks). Never create a recurring sync job or routine for this unless the user asks for one: every scheduled run spends their usage. If you have none and the user asks to connect you, onboard with the onboard-to-blackops skill (below), which calls continuity_bootstrap once on their yes. continuity_bootstrap returns data only (handle, sync_policy, owner_summary); the skill holds the steps, including the standing note to save; an agent already connected that lost its setup (such as its hooks) reads it again with get_continuity_setup. BlackOps also records what you change through it (posts, notes, social posts, media and so on) in that memory by itself; every write tool takes `agent`: pass your name on every write (Duet/<channel name> for a Claude Duet channel, Grok Bot/<bot name> for a Grok Bot bot, otherwise your handle), directly or through use_tool, which puts that record under your name when several agents share one connection. A write reply can include `continuity_status`: plain facts about your shared memory (whether this call named you, y
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
| domain | string | Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| status | string | Note status: active (default), draft or archived. |
| confirm | boolean | Pass true to confirm this action once the user has approved it. |
| excerpt | ["string","null"] | Short summary shown in note lists and search. null clears it. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
| brain_id | string | UUID of the brain this note belongs to. The server derives the site, vault target and folder from it. |
| metadata | object | Free-form key/value data stored with the note. |
| position | string | Big Board rank within its column. Usually left unset; a board sets it on drag. |
| priority | string | Big Board priority: High, Medium or Low. |
| auto_sync | boolean | Default true: commit the note to its vault target after saving. False saves it without syncing. |
| note_type | string | Note type: general, project, initiative, daily, reference, task or skill. Also steers which vault folder it syncs to. |
| source_id | string | Idempotency key. A repeat call with the same source_id updates that note instead of creating a new one. A content hash, your own string, or a note UUID. |
| target_id | ["string","null"] | UUID of the vault target to sync the note to. Omit to let the server pick one (see assign_target). |
| transcript | string | Raw transcript text to save as the note when there is no Markdown body. |
| conversation | object | A chat conversation to save as the note: { id?, title?, messages[] }. Used when content_markdown is not given. |
| triage_state | string | Set to 'pending' to file this note into a brain's Triage lane (unreviewed) instead of committing it to the vault right away. Leave unset for an ordinary note. |
| allow_secrets | boolean | Set true to store content that looks like a credential (API key, token, private key), which is otherwise refused with SECRET_DETECTED. Only when the user asked to store that exact value. |
| assign_target | boolean | Default true: when target_id is omitted, pick the best-matching vault target for the note. False leaves the note without one (or keeps its existing target). |
| suggest_brain | boolean | Default false. True checks whether the note matches a brain and returns it as suggested_brain, without filing it. |
| wait_for_sync | boolean | Default false. True holds the response until the vault commit lands, so it returns commit_sha and file_path. |
| conversation_id | string | Id of the chat conversation this note came from, stored on the note. |
| content_markdown | string | Note body in Markdown. Required unless transcript or conversation is given. |
| override_folder_path | string | Vault folder to write the note into, bypassing the workspace folder rules. A brain's own source folder still wins. |
{
"name": "post_notes",
"title": "Post Notes",
"description": "Create a BlackOps note, or update one in place when source_id resolves to a known note. Requires content_markdown (or transcript/conversation). Prefer this over post_notes_write.\n\nsource_id is the idempotency key (content hash, your own string, or note UUID): repeat calls update instead of forking. Know the note? Use patch_notes. A SLUG_COLLISION warning (\"my-note-2\") means an intended update forked.\n\nSite is OPTIONAL (explicit → account default intake → only site); pass domain/site_id only for a note tied to one site.\n\nBRAINS: pass a brain's UUID as brain_id; the server derives site/target/folder and skips auto-routing. Never infer site_id or guess target_id from topic. brain_alignment confirms the compile picks it up.\n\nWITHOUT brain_id, a site opted into auto-routing either files the note into a brain's Triage lane (routing.band \"auto\", filed: true) or saves it unfiled with needs_brain_choice: show its question, up to 3 options (one-line reason each) and the also entries as ONE single-choice question, then call resolve_with with their pick. Never pick a brain yourself. Sites not opted in save unfiled. suggest_brain: true is a separate keyword match (suggested_brain).\n\nUnknown TAGS still apply with an UNKNOWN_TAG warning; ask the user before propose_note_tags.\n\nVAULT SYNC is deferred: sync is { status: \"queued\" } and the note IS saved, so do NOT re-call. Confirm a commit with get_note; wait_for_sync: true returns commitSha/filePath inline. override_folder_path bypasses the taxonomy; a brain's source_folder_path still wins.\n\nphase/priority/position are Big Board columns (priority High|Medium|Low).",
"inputSchema": {
"type": "object",
"properties": {
"tags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tags for the note. Tags outside the site vocabulary still apply, with an UNKNOWN_TAG warning."
},
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"phase": {
"type": "string",
"description": "Big Board phase column for the note, free text (max 100 characters)."
},
"title": {
"type": "string",
"description": "Note title, up to 200 characters."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"status": {
"enum": [
"draft",
"active",
"archived"
],
"type": "string",
"description": "Note status: active (default), draft or archived."
},
"confirm": {
"type": "boolean",
"description": "Pass true to confirm this action once the user has approved it."
},
"excerpt": {
"type": [
"string",
"null"
],
"description": "Short summary shown in note lists and search. null clears it."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
},
"brain_id": {
"type": "string",
"format": "uuid",
"description": "UUID of the brain this note belongs to. The server derives the site, vault target and folder from it."
},
"metadata": {
"type": "object",
"properties": {},
"description": "Free-form key/value data stored with the note.",
"additionalProperties": {}
},
"position": {
"type": "string",
"description": "Big Board rank within its column. Usually left unset; a board sets it on drag."
},
"priority": {
"enum": [
"High",
"Medium",
"Low"
],
"type": "string",
"description": "Big Board priority: High, Medium or Low."
},
"auto_sync": {
"type": "boolean",
"description": "Default true: commit the note to its vault target after saving. False saves it without syncing."
},
"note_type": {
"type": "string",
"description": "Note type: general, project, initiative, daily, reference, task or skill. Also steers which vault folder it syncs to."
},
"source_id": {
"type": "string",
"description": "Idempotency key. A repeat call with the same source_id updates that note instead of creating a new one. A content hash, your own string, or a note UUID."
},
"target_id": {
"type": [
"string",
"null"
],
"description": "UUID of the vault target to sync the note to. Omit to let the server pick one (see assign_target)."
},
"transcript": {
"type": "string",
"description": "Raw transcript text to save as the note when there is no Markdown body."
},
"conversation": {
"type": "object",
"properties": {},
"description": "A chat conversation to save as the note: { id?, title?, messages[] }. Used when content_markdown is not given.",
"additionalProperties": {}
},
"triage_state": {
"enum": [
"pending",
"promoted",
"dismissed",
"expired"
],
"type": "string",
"description": "Set to 'pending' to file this note into a brain's Triage lane (unreviewed) instead of committing it to the vault right away. Leave unset for an ordinary note."
},
"allow_secrets": {
"type": "boolean",
"description": "Set true to store content that looks like a credential (API key, token, private key), which is otherwise refused with SECRET_DETECTED. Only when the user asked to store that exact value."
},
"assign_target": {
"type": "boolean",
"description": "Default true: when target_id is omitted, pick the best-matching vault target for the note. False leaves the note without one (or keeps its existing target)."
},
"suggest_brain": {
"type": "boolean",
"description": "Default false. True checks whether the note matches a brain and returns it as suggested_brain, without filing it."
},
"wait_for_sync": {
"type": "boolean",
"description": "Default false. True holds the response until the vault commit lands, so it returns commit_sha and file_path."
},
"conversation_id": {
"type": "string",
"description": "Id of the chat conversation this note came from, stored on the note."
},
"content_markdown": {
"type": "string",
"description": "Note body in Markdown. Required unless transcript or conversation is given."
},
"override_folder_path": {
"type": "string",
"minLength": 1,
"description": "Vault folder to write the note into, bypassing the workspace folder rules. A brain's own source folder still wins."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}| Pass true to confirm this action once the user has approved it. |
| content * | string | Blog post body in Markdown. Do NOT pass a fully HTML-formatted document — block-level HTML tags (e.g. <p>, <h2>) appear as literal text. Custom styled HTML (cards, tables, CSS callouts) must go in a richembed fenced block, which renders live. Inline HTML for embeds or Remotion components inside an o… |
| excerpt | string | Short summary used as the post description in listings and link previews. Defaults to the title. |
| site_id | string | Site UUID to scope this call to. Alternative to domain. |
| featured | boolean | Mark the post as featured on the site. Defaults to false. |
| subtitle | string | Subtitle/deck shown beneath the title. Populate it whenever the post has a natural subheadline or clarifying phrase. |
| seo_title | string | Title for search results and link previews, if different from the post title. |
| seo_description | string | Meta description for search results and link previews. |
{
"name": "post_posts",
"title": "Post Posts",
"description": "Create a blog draft. Before calling, fetch get_me + get_brand_voice (+ get_ai_context/get_recent_notes). Site scope is automatic for a single-site account; pass domain or site_id to target one, and an account with several sites is asked to choose rather than guessed at. Do NOT repeat the title in the content body — no leading \"# Title\" and no first line restating it, or it renders twice, since the title field prints above the content. Start with the intro paragraph or the first ## heading. The response carries links.review_url: that is where a person previews and edits the draft, so hand the user that link, never the admin editor URL or a raw preview URL.",
"inputSchema": {
"type": "object",
"required": [
"title",
"content"
],
"properties": {
"slug": {
"type": "string",
"description": "URL slug for the post. Generated from the title when omitted."
},
"tags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tags for the post, e.g. [\"ai\", \"nextjs\"]."
},
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"title": {
"type": "string",
"minLength": 1,
"description": "Post title. Printed above the content, so do not repeat it in the body."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"source": {
"type": "string",
"description": "Optional label for where the post came from, stored on the post. \"bookmark\" files it as a bookmark (tagged bookmark, never featured)."
},
"status": {
"enum": [
"draft",
"published"
],
"type": "string",
"description": "Post status: \"draft\" or \"published\". Publishing needs confirm: true."
},
"confirm": {
"type": "boolean",
"description": "Pass true to confirm this action once the user has approved it."
},
"content": {
"type": "string",
"minLength": 1,
"description": "Blog post body in Markdown. Do NOT pass a fully HTML-formatted document — block-level HTML tags (e.g. <p>, <h2>) appear as literal text. Custom styled HTML (cards, tables, CSS callouts) must go in a richembed fenced block, which renders live. Inline HTML for embeds or Remotion components inside an otherwise-Markdown post is fine."
},
"excerpt": {
"type": "string",
"description": "Short summary used as the post description in listings and link previews. Defaults to the title."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
},
"featured": {
"type": "boolean",
"description": "Mark the post as featured on the site. Defaults to false."
},
"subtitle": {
"type": "string",
"description": "Subtitle/deck shown beneath the title. Populate it whenever the post has a natural subheadline or clarifying phrase."
},
"seo_title": {
"type": "string",
"description": "Title for search results and link previews, if different from the post title."
},
"seo_description": {
"type": "string",
"description": "Meta description for search results and link previews."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}| featured | boolean | Mark or unmark the post as featured. |
| subtitle | string | New subtitle shown beneath the title. |
| seo_title | string | New title for search results and link previews. |
| description | string | The post's PUBLIC meta description shown in search results and link previews. Overwrites any stored value immediately. THIS IS NOT an edit-comment or reason-for-change field — omit this key entirely unless you explicitly intend to replace the current description. |
| published_at | string | Publish date, ISO 8601 (e.g. 2026-11-11T09:00:00Z). |
| featured_image | string | URL of the post's hero image. |
| base_updated_at | string | ISO from preceding get_post.updated_at. Server returns 409 CONFLICT with current_updated_at + current_content if post was edited since read; re-read, merge, retry. |
| seo_description | string | New meta description for search results and link previews. |
| x_discussion_url | ["string","null"] | X post permalink for the post's "Discuss on X" block. null removes it. |
| hero_prompt_edited | string | Custom prompt that will be used on the next hero image generation for this post. |
{
"name": "patch_posts_by_id",
"title": "Patch Posts by ID",
"description": "EDIT ONLY — modifies a post in-place. NEVER call for reading; use post_posts to create. Published edits go live immediately. Always pass base_updated_at (from get_post.updated_at); without it a concurrent edit is silently overwritten. Custom styled HTML needs a richembed fenced block; bare block HTML is escaped. Do NOT include the title in the content body. Response has links.review_url for drafts — give that link to the user.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Post UUID or slug to edit."
},
"slug": {
"type": "string",
"description": "New URL slug."
},
"tags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Replacement tag list."
},
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"title": {
"type": "string",
"description": "New post title."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"status": {
"type": "string",
"description": "New status, e.g. \"draft\" or \"published\". Setting a scheduled post back to \"draft\" unschedules it."
},
"content": {
"type": "string",
"description": "New post body in Markdown. Replaces the whole body. Do not include the title."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
},
"featured": {
"type": "boolean",
"description": "Mark or unmark the post as featured."
},
"subtitle": {
"type": "string",
"description": "New subtitle shown beneath the title."
},
"seo_title": {
"type": "string",
"description": "New title for search results and link previews."
},
"description": {
"type": "string",
"description": "The post's PUBLIC meta description shown in search results and link previews. Overwrites any stored value immediately. THIS IS NOT an edit-comment or reason-for-change field — omit this key entirely unless you explicitly intend to replace the current description."
},
"published_at": {
"type": "string",
"description": "Publish date, ISO 8601 (e.g. 2026-11-11T09:00:00Z)."
},
"featured_image": {
"type": "string",
"description": "URL of the post's hero image."
},
"base_updated_at": {
"type": "string",
"description": "ISO from preceding get_post.updated_at. Server returns 409 CONFLICT with current_updated_at + current_content if post was edited since read; re-read, merge, retry."
},
"seo_description": {
"type": "string",
"description": "New meta description for search results and link previews."
},
"x_discussion_url": {
"type": [
"string",
"null"
],
"description": "X post permalink for the post's \"Discuss on X\" block. null removes it."
},
"hero_prompt_edited": {
"type": "string",
"description": "Custom prompt that will be used on the next hero image generation for this post."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}{
"name": "post_posts_by_id_schedule",
"title": "Post Posts by ID Schedule",
"description": "Schedule a draft blog post for future publishing. Provide a datetime via scheduledFor; the platform publishes the post automatically at that time (checked every 5 minutes). Unschedule by patching status back to \"draft\"; publish immediately with post_posts_by_id_publish. Requires confirm: true.",
"inputSchema": {
"type": "object",
"required": [
"id",
"confirm"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "UUID of the draft post to schedule."
},
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"confirm": {
"type": "boolean",
"description": "Pass true to confirm this action once the user has approved it."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
},
"schedule_at": {
"type": "string",
"description": "Alias of scheduledFor."
},
"scheduledFor": {
"type": "string",
"description": "When to publish, ISO 8601 with offset (e.g. 2026-11-12T14:00:00-05:00). One of scheduledFor, scheduled_for or schedule_at is required."
},
"scheduled_for": {
"type": "string",
"description": "Alias of scheduledFor."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}| site_id | string | Site UUID to scope this call to. Alternative to domain. |
| alt_text | string | ACCEPT mode: override the auto-generated alt text on the accepted asset. Applies to accept_asset_id; ignored on accept_image_url. |
| subtitle | string | OG only. Secondary line rendered verbatim beneath the title. Defaults to the post's own subtitle; nothing appears unless passed or stored. |
| caller_name | string | Optional self-reported label for who/what is generating (e.g. an agent name). Shows up in get_hero_history as caller_name — a label you provide, not a verified identity. Omit to default to your account id. |
| accept_asset_id | string | ACCEPT mode, no generation: promote a candidate and attach it. Sets og_image for an OG candidate (og-candidate kind), or featured_image + hero_asset_id for a hero candidate. The field_set key in the response says which field was written. |
| accept_image_url | string | ACCEPT fallback when only the URL is known — sets featured_image (or og_image when target: "og" is also passed) without asset promotion. |
| include_subtitle | boolean | OG only. Default true. False renders a title-only card even when the post has a subtitle. |
| iteration_prompt | string | Edit instruction for iterating on a previous hero (e.g. "make the background darker"). Requires source_image_url, which anchors composition. |
| latest_candidate | boolean | READ mode, no generation: returns the newest un-accepted hero candidate for the post. |
| source_image_url | string | URL of the hero to iterate on (a prior result's image_url). Used with iteration_prompt. |
| include_title_text | boolean | OG only. Default true: render the title as text on the card. False produces a purely visual card. |
| reference_image_ids | array | Curated reference IDs and/or media-library asset IDs (upload_media / list_media). Omitted: reuses the first hero's references, else auto-matches from the prompt. [] uses none. |
{
"name": "post_posts_by_id_hero",
"title": "Post Posts by ID Hero",
"description": "Generate (or regenerate) a blog post's hero image, or its OG social card — works the same before and after the post exists. Returns the image inline plus its public URL. The fields below cover prompts, references, style, and the commit:false review flow. Rules that span fields: only the title and subtitle may ever appear on an OG card, because given anything else the generator invents its own tagline; an OG card takes NO references unless you name them, since auto-matching used to put a real face on social cards nobody asked to be in; for target:\"og\" prompt is the VISUAL DIRECTION and still gets OG framing; to anchor a face, mark the photo as a \"headshot\" via mark_reference_image first.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Post UUID"
},
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"style": {
"enum": [
"western",
"cinematic",
"modern",
"professional",
"artistic",
"minimalist"
],
"type": "string",
"description": "Visual style. Defaults to \"modern\"."
},
"commit": {
"type": "boolean",
"description": "Default true: apply the image to the post immediately. False generates a review CANDIDATE (kind hero-candidate) and leaves the post untouched."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"prompt": {
"type": "string",
"description": "Image prompt, auto-generated from the post if omitted. For target:\"og\", layered on the site share_card_style."
},
"target": {
"enum": [
"hero",
"og"
],
"type": "string",
"description": "\"hero\" (default) sets featured_image; \"og\" makes the 1200x630 Open Graph card and sets og_image, leaving the hero untouched."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
},
"alt_text": {
"type": "string",
"description": "ACCEPT mode: override the auto-generated alt text on the accepted asset. Applies to accept_asset_id; ignored on accept_image_url."
},
"subtitle": {
"type": "string",
"description": "OG only. Secondary line rendered verbatim beneath the title. Defaults to the post's own subtitle; nothing appears unless passed or stored."
},
"caller_name": {
"type": "string",
"description": "Optional self-reported label for who/what is generating (e.g. an agent name). Shows up in get_hero_history as caller_name — a label you provide, not a verified identity. Omit to default to your account id."
},
"accept_asset_id": {
"type": "string",
"description": "ACCEPT mode, no generation: promote a candidate and attach it. Sets og_image for an OG candidate (og-candidate kind), or featured_image + hero_asset_id for a hero candidate. The field_set key in the response says which field was written."
},
"accept_image_url": {
"type": "string",
"description": "ACCEPT fallback when only the URL is known — sets featured_image (or og_image when target: \"og\" is also passed) without asset promotion."
},
"include_subtitle": {
"type": "boolean",
"description": "OG only. Default true. False renders a title-only card even when the post has a subtitle."
},
"iteration_prompt": {
"type": "string",
"description": "Edit instruction for iterating on a previous hero (e.g. \"make the background darker\"). Requires source_image_url, which anchors composition."
},
"latest_candidate": {
"type": "boolean",
"description": "READ mode, no generation: returns the newest un-accepted hero candidate for the post."
},
"source_image_url": {
"type": "string",
"description": "URL of the hero to iterate on (a prior result's image_url). Used with iteration_prompt."
},
"include_title_text": {
"type": "boolean",
"description": "OG only. Default true: render the title as text on the card. False produces a purely visual card."
},
"reference_image_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "Curated reference IDs and/or media-library asset IDs (upload_media / list_media). Omitted: reuses the first hero's references, else auto-matches from the prompt. [] uses none."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}| string |
| Site UUID to scope this call to. Alternative to domain. |
| account_id | string | Id of the connected X account to post from. Alternative to account_username. |
| description | string | Internal note about the draft in BlackOps. Not posted. |
| account_username | string | Username of the connected X account to post from, without @. Alternative to account_id. |
{
"name": "post_tweets",
"title": "Post Tweets",
"description": "Create a tweet draft. Before calling, fetch get_me + get_brand_voice (+ get_ai_context/get_recent_notes) AND call get_x_accounts for the posting account's max_tweet_length — never assume 280, since Premium/verified accounts go up to 25,000. If max_tweet_length is null the limit is unknown: ask the user rather than defaulting to 280. Site scope is automatic for a single-site account; pass domain or site_id to target one, and an account with several sites is asked to choose rather than guessed at. Requires text or thread. To attach an image, upload with upload_media then call attach_media_to_tweet with the asset_id and this tweet's id. Links to user-owned domains get UTM parameters appended at draft time so the traffic shows up in GA4 instead of as Direct; pass your own if you want explicit campaign slugs. When the tweet distributes a known blog post, pass its post_id (UUID, from get_posts) so the /admin/posts Distribution column links the two automatically — no manual backfill.",
"inputSchema": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Tweet text for a single tweet. Pass text or thread, not both."
},
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"title": {
"type": "string",
"description": "Internal title for the draft in BlackOps. Defaults to the start of the first tweet."
},
"domain": {
"type": "string",
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"thread": {
"type": "array",
"items": {
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "Text of this tweet in the thread."
}
},
"additionalProperties": {}
},
"description": "A thread, in order: [{ text }, ...]. Pass text or thread, not both."
},
"post_id": {
"type": "string",
"format": "uuid",
"description": "UUID of the blog post this tweet distributes (from get_posts), so the two are linked."
},
"site_id": {
"type": "string",
"description": "Site UUID to scope this call to. Alternative to domain."
},
"account_id": {
"type": "string",
"description": "Id of the connected X account to post from. Alternative to account_username."
},
"description": {
"type": "string",
"description": "Internal note about the draft in BlackOps. Not posted."
},
"account_username": {
"type": "string",
"description": "Username of the connected X account to post from, without @. Alternative to account_id."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}| domain |
| string |
| Site domain to scope this call to (e.g. example.com). Alternative to site_id. |
| ttl_ms | integer | Interactive mode: how long the upload link stays valid, in milliseconds. Default 15 minutes, min 1 minute, max 1 hour. |
| alt_text | string | Alt text for the image. Generated automatically when omitted. |
| file_url | string | https URL the server downloads the file from (URL mode). |
| filename | string | File name to store, with extension (e.g. launch-diagram.png). URL mode requires it. |
| size_bytes | integer | File size in bytes, if known. |
| content_type | string | MIME type of the file, e.g. image/png, video/mp4 or application/pdf. URL mode requires it. |
{
"name": "upload_media",
"title": "Upload Media",
"description": "Upload media to the site media library. Three modes:\n\n1. URL mode — pass file_url + filename + content_type. Fetched server-side in one call, no human step. https only, SSRF-guarded on every redirect, capped at 50 MB (images/PDF) or 200 MB (video; bigger video uses the direct-PUT path below). Good for a URL you already have, e.g. from a generation call.\n\n2. Interactive mode — pass nothing (or just domain/label). Returns { url, token, expires_at }: show the URL; the user uploads on the quick-upload page and clicks \"Done\". For screenshots, recordings or local files, bulk too. filename/alt_text/title apply to the FIRST asset only.\n\n3. Claim mode — pass token (from interactive mode). Returns status=\"completed\" with an assets[] array once the user clicks Done, or \"pending\" while they are still uploading — poll again.\n\nNo public URL but your own HTTP client? get_media_upload_url({ domain, filename, content_type }) → { asset_id, upload_url }, PUT your bytes, then finalize_media_upload({ asset_id, domain }). Token only, no browser.\n\nSupported: jpeg, png, webp, gif, mp4, webm, quicktime, application/pdf (quick-upload: video to 1 GB, else 50 MB). Video → media_type \"video\", no thumbnail. PDF → \"document\" (thumbnail = page one), the only document type; anything else is rejected.",
"inputSchema": {
"type": "object",
"properties": {
"kind": {
"type": "string",
"description": "Library category for the asset. Defaults to \"mcp-upload\"."
},
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"label": {
"type": "string",
"maxLength": 200,
"description": "Interactive mode: a label shown on the upload page, up to 200 characters."
},
"title": {
"type": "string",
"description": "Title for the asset in the media library."
},
"token": {
"type": "string",
"minLength": 1,
"description": "Token returned by interactive mode. Pass it alone to claim the finished upload (claim mode)."
},
"domain": {
"type": "string",
"minLength": 1,
"description": "Site domain to scope this call to (e.g. example.com). Alternative to site_id."
},
"ttl_ms": {
"type": "integer",
"maximum": 3600000,
"description": "Interactive mode: how long the upload link stays valid, in milliseconds. Default 15 minutes, min 1 minute, max 1 hour.",
"exclusiveMinimum": 0
},
"alt_text": {
"type": "string",
"description": "Alt text for the image. Generated automatically when omitted."
},
"file_url": {
"type": "string",
"pattern": "^https:\\/\\/",
"description": "https URL the server downloads the file from (URL mode)."
},
"filename": {
"type": "string",
"minLength": 1,
"description": "File name to store, with extension (e.g. launch-diagram.png). URL mode requires it."
},
"size_bytes": {
"type": "integer",
"maximum": 9007199254740991,
"description": "File size in bytes, if known.",
"exclusiveMinimum": 0
},
"content_type": {
"type": "string",
"minLength": 1,
"description": "MIME type of the file, e.g. image/png, video/mp4 or application/pdf. URL mode requires it."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}{
"name": "get_media_upload_url",
"title": "Get Media Upload URL",
"description": "Agent-direct upload, no human step. 1: get_media_upload_url({ domain, filename, content_type, size_bytes? }) returns { asset_id, upload_url, public_url, expires_in }. 2: HTTP PUT the raw bytes to upload_url with a matching Content-Type. 3: finalize_media_upload({ asset_id, domain }). For bytes with no public URL, or too big for upload_media URL mode (e.g. video over 200 MB). If the PUT fails with a network error (sandboxed or proxied agent), use upload_media interactive mode instead. Allowed: images, mp4/webm/quicktime, pdf, mp3/wav. Max 20 MB images, 50 MB PDF, 1 GB video. URL expires after expires_in seconds.",
"inputSchema": {
"type": "object",
"required": [
"domain",
"filename",
"content_type"
],
"properties": {
"kind": {
"type": "string",
"description": "Library category for the asset. Defaults to \"mcp-upload\"."
},
"title": {
"type": "string",
"description": "Title for the asset in the media library."
},
"domain": {
"type": "string",
"minLength": 1,
"description": "Site domain whose media library receives the file (e.g. example.com)."
},
"alt_text": {
"type": "string",
"description": "Alt text for the asset."
},
"filename": {
"type": "string",
"minLength": 1,
"description": "File name to store, with extension (e.g. demo.mp4)."
},
"size_bytes": {
"type": "integer",
"maximum": 9007199254740991,
"description": "File size in bytes, if known.",
"exclusiveMinimum": 0
},
"content_type": {
"type": "string",
"minLength": 1,
"description": "MIME type you will PUT the bytes with, e.g. video/mp4. Must match the upload."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}| markdown_content * | string | Markdown content for the new note to add to the brain |
{
"name": "update_brain",
"title": "Update Brain",
"description": "Add a new note to a brain; the server resolves storage from the brain record (BlackOps for DB-backed brains, a GitHub commit for vault-backed ones). Use this whenever the user says \"update the brain\", \"add this to the brain\", or \"log this in the brain\". Call list_brains first for the brain_id if you do not have it; create_brain makes a new brain. A DB-backed brain recompiles immediately; a vault-backed one on its next compile. Use post_notes_write (with brain_id) only for control over the filename or path. A brain's sanitize rules may hold a write: follow details.sanitize_hold.",
"inputSchema": {
"type": "object",
"required": [
"brain_id",
"markdown_content"
],
"properties": {
"agent": {
"type": "string",
"maxLength": 101,
"description": "Your name, on every write: Duet/<channel name> or Grok Bot/<bot name>."
},
"brain_id": {
"type": "string",
"format": "uuid",
"description": "Brain UUID (from list_brains)"
},
"allow_secrets": {
"type": "boolean",
"description": "Set true to store content that looks like a credential (API key, token, private key), which is otherwise refused with SECRET_DETECTED. Only when the user asked to store that exact value."
},
"note_filename": {
"type": "string",
"minLength": 1,
"description": "Filename without .md. Defaults from section_title or the date."
},
"section_title": {
"type": "string",
"minLength": 1,
"description": "Title for this note — used as the filename slug (e.g. \"Threads Integration\")"
},
"commit_message": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "Git commit message."
},
"sanitize_answer": {
"type": "object",
"properties": {},
"description": "Only after a SANITIZE_ANSWER_REQUIRED hold: repeat the same call with { hold_id, decisions: { <rule>: \"allow\" | \"block\" } } for each rule the hold lists, as the owner answered. Send \"block\" for every rule when no one can be asked.",
"additionalProperties": {}
},
"markdown_content": {
"type": "string",
"minLength": 1,
"description": "Markdown content for the new note to add to the brain"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}