DreamAgent is an MCP server published by io.github.nivethaug, hosted at mcp.dreamagent.cloud. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 24 tools, including dreamagent_list_projects, dreamagent_list_global_integrations, dreamagent_list_project_env, dreamagent_list_superpowers, dreamagent_list_files.
Build and deploy websites, Telegram and Discord bots from chat via the DreamAgent platform.
Nothing else in the archive shares these values.
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.
List the user's DreamAgent projects. Returns each project's name, ID, type, status, and live domain (when available). Project names resolve to IDs here.
| Parameter | Type | Description |
|---|---|---|
| status | any | optional exact-match filter (e.g. 'ready', 'failed'). During creation, projects report intermediate phases (creating/building/deploying/…), so filtering by 'creating' does not match every in-progress project. |
{
"name": "dreamagent_list_projects",
"title": "List DreamAgent projects",
"description": "List the user's DreamAgent projects.\n\nReturns each project's name, ID, type, status, and live domain (when\navailable). Project names resolve to IDs here.",
"inputSchema": {
"type": "object",
"properties": {
"status": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "optional exact-match filter (e.g. 'ready', 'failed').\nDuring creation, projects report intermediate phases\n(creating/building/deploying/…), so filtering by 'creating'\ndoes not match every in-progress project."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}List the user's saved credentials (Global Integrations). Saved credentials are referenced by ID when creating projects: bot_token_integration_id for bot tokens, global_integration_ids for other keys. Secret values are never returned — only IDs and metadata (type, key name, verified, title). New credentials are added at dreamagent.cloud → Settings → Global Integrations.
No parameters.
{
"name": "dreamagent_list_global_integrations",
"title": "List connected integrations",
"description": "List the user's saved credentials (Global Integrations).\n\nSaved credentials are referenced by ID when creating projects:\nbot_token_integration_id for bot tokens, global_integration_ids for\nother keys. Secret values are never returned — only IDs and metadata\n(type, key name, verified, title). New credentials are added at\ndreamagent.cloud → Settings → Global Integrations.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}List a project's environment variables with their details. Shows each key's name, title, description, docs URL, and category — values are masked (secrets are never returned). Use to see which integrations a project already has before adding more, or to answer "what keys does my project have?". These are PROJECT-SPECIFIC variables — distinct from the user's Global Integrations — API-key credentials and connected OAuth services (dreamagent_list_global_integrations).
| Parameter | Type | Description |
|---|---|---|
| project_id * | integer | the project to inspect. |
{
"name": "dreamagent_list_project_env",
"title": "List project environment variables",
"description": "List a project's environment variables with their details.\n\nShows each key's name, title, description, docs URL, and category —\nvalues are masked (secrets are never returned). Use to see which\nintegrations a project already has before adding more, or to answer\n\"what keys does my project have?\".\n\nThese are PROJECT-SPECIFIC variables — distinct from the user's\nGlobal Integrations — API-key credentials and connected OAuth services (dreamagent_list_global_integrations).",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"project_id": {
"type": "integer",
"description": "the project to inspect."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}List the account's add-on tools (Superpowers) with their enabled state. Read-only; no usage consumed. Tools shown as enabled can be used from the user's projects through dreamagent_chat by naming the feature in the message.
No parameters.
{
"name": "dreamagent_list_superpowers",
"title": "List available superpowers",
"description": "List the account's add-on tools (Superpowers) with their enabled\nstate. Read-only; no usage consumed.\n\nTools shown as enabled can be used from the user's projects through\ndreamagent_chat by naming the feature in the message.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}List the file tree of a DreamAgent project (source files only — hidden files like .env are excluded). Use before reading or editing a file to find the correct path.
| Parameter | Type | Description |
|---|---|---|
| project_id * | integer |
{
"name": "dreamagent_list_files",
"title": "List project files",
"description": "List the file tree of a DreamAgent project (source files only —\nhidden files like .env are excluded). Use before reading or editing\na file to find the correct path.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"project_id": {
"type": "integer"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Read a source file from a DreamAgent project. file_path is the project-relative path (from dreamagent_list_files), e.g. "src/pages/Home.tsx" or "telegram/main.py". Hidden files (.env) and binaries are not readable.
| Parameter | Type | Description |
|---|---|---|
| file_path * | string | |
| project_id * | integer |
{
"name": "dreamagent_read_file",
"title": "Read a project file",
"description": "Read a source file from a DreamAgent project. file_path is the\nproject-relative path (from dreamagent_list_files), e.g.\n\"src/pages/Home.tsx\" or \"telegram/main.py\". Hidden files (.env) and\nbinaries are not readable.",
"inputSchema": {
"type": "object",
"required": [
"project_id",
"file_path"
],
"properties": {
"file_path": {
"type": "string"
},
"project_id": {
"type": "integer"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}WRITE ACTION — make SMALL targeted changes to an EXISTING file in a DreamAgent project via exact search/replace. PREFERRED over dreamagent_write_file for editing existing files: you send only the changed fragments (never the whole file) — cheaper, immune to payload size/safety blocks in the calling client, and cannot corrupt unchanged code. Use dreamagent_write_file only to CREATE files or for full rewrites. Read the file first (dreamagent_read_file) and copy each 'find' text EXACTLY as it appears — whitespace and indentation must match. All edits are validated BEFORE anything is saved; if any 'find' fails to match, the file is left untouched and the error tells you which edit and why.
| Parameter | Type | Description |
|---|---|---|
| edits * | array | list of edit objects: {"find": "<exact existing text>", "replace": "<new text>", "all": false} # optional: replace every occurrence |
| confirm | boolean | must be true to execute. |
| file_path * | string | project-relative path of the EXISTING file to edit. |
| project_id * | integer | project containing the file. |
| auto_commit | boolean | commit+push and record version history after saving (default true; pass false to batch several edit_file calls and finish with one dreamagent_commit_push). |
WRITE ACTION — overwrite or create one source file in a DreamAgent project with the exact content given. For CHANGING an existing file, prefer dreamagent_edit_file (small targeted find→replace edits — no need to send the whole file). By default the write is immediately committed and pushed to the project's GitHub repo and recorded in its session history & version history (so the user can restore/revert). Changes go live after the project is rebuilt (dreamagent_build_publish). MULTI-FILE EDITS: pass auto_commit=false on each write, then call dreamagent_commit_push once at the end — one commit and one history entry for the whole batch. GUARDS (enforced server-side, the same as the in-app code editor): path stays inside the project, hidden/credential files (.env, .git, keys) are rejected, content is scanned for malware/shell signatures and blocked, 2MB size cap. Failed scans return the reason. The user can undo damage by editing in the DreamAgent editor or restoring a previous version from version history — still, prefer precise minimal diffs.
| Parameter | Type | Description |
|---|---|---|
| confirm | boolean | |
| content * | string | |
| file_path * | string | |
| project_id * | integer | |
| auto_commit | boolean |
{
"name": "dreamagent_write_file",
"title": "Write a project file",
"description": "WRITE ACTION — overwrite or create one source file in a DreamAgent\nproject with the exact content given. For CHANGING an existing file,\nprefer dreamagent_edit_file (small targeted find→replace edits — no\nneed to send the whole file). By default the write is\nimmediately committed and pushed to the project's GitHub repo and\nrecorded in its session history & version history (so the user can\nrestore/revert). Changes go live after the project is rebuilt\n(dreamagent_build_publish).\n\nMULTI-FILE EDITS: pass auto_commit=false on each write, then call\ndreamagent_commit_push once at the end — one commit and one history\nentry for the whole batch.\n\nGUARDS (enforced server-side, the same as the in-app code editor):\npath stays inside the project, hidden/credential files (.env, .git,\nkeys) are rejected, content is scanned for malware/shell signatures\nand blocked, 2MB size cap. Failed scans return the reason.\n\nThe user can undo damage by editing in the DreamAgent editor or\nrestoring a previous version from version history — still, prefer\nprecise minimal diffs.",
"inputSchema": {
"type": "object",
"required": [
"project_id",
"file_path",
"content"
],
"properties": {
"confirm": {
"type": "boolean",
"default": false
},
"content": {
"type": "string"
},
"file_path": {
"type": "string"
},
"project_id": {
"type": "integer"
},
"auto_commit": {
"type": "boolean",
"default": true
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Git diff of one project file against the last commit — shows the pending (not yet live) changes. Free, read-only. Use after edits to review exactly what changed before rebuilding.
| Parameter | Type | Description |
|---|---|---|
| file_path * | string | |
| project_id * | integer |
{
"name": "dreamagent_get_file_diff",
"title": "Show file changes vs last commit",
"description": "Git diff of one project file against the last commit — shows the\npending (not yet live) changes. Free, read-only. Use after edits to\nreview exactly what changed before rebuilding.",
"inputSchema": {
"type": "object",
"required": [
"project_id",
"file_path"
],
"properties": {
"file_path": {
"type": "string"
},
"project_id": {
"type": "integer"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}WRITE ACTION — delete one source file from a DreamAgent project. Hidden/credential files (.env, .git, keys) are rejected. By default the deletion is immediately committed and pushed (so it is recorded in session history & version history) — deleted files stay recoverable via git history / version restore. confirm must be true to execute.
| Parameter | Type | Description |
|---|---|---|
| confirm | boolean | |
| file_path * | string | |
| project_id * | integer | |
| auto_commit | boolean |
{
"name": "dreamagent_delete_file",
"title": "Delete a project file",
"description": "WRITE ACTION — delete one source file from a DreamAgent project.\nHidden/credential files (.env, .git, keys) are rejected. By default the\ndeletion is immediately committed and pushed (so it is recorded in\nsession history & version history) — deleted files stay recoverable\nvia git history / version restore. confirm must be true to execute.",
"inputSchema": {
"type": "object",
"required": [
"project_id",
"file_path"
],
"properties": {
"confirm": {
"type": "boolean",
"default": false
},
"file_path": {
"type": "string"
},
"project_id": {
"type": "integer"
},
"auto_commit": {
"type": "boolean",
"default": true
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}WRITE ACTION — commit ALL pending changes in a DreamAgent project and push them to its private GitHub repo. The commit gets its own entry in the project's session history and version history, so the user can restore/revert to it in the DreamAgent dashboard. Use it to (a) commit several MCP writes/deletes as ONE version — write and delete with auto_commit=false first — or (b) retry a commit after a failure. Chat-driven edits commit automatically; this tool is for direct file changes made through MCP.
| Parameter | Type | Description |
|---|---|---|
| confirm | boolean | must be true to execute |
| message | string | short commit message, e.g. "Update landing hero section" (default "MCP edit: project <id>") |
| project_id * | integer | project to commit |
{
"name": "dreamagent_commit_push",
"title": "Commit and push project changes",
"description": "WRITE ACTION — commit ALL pending changes in a DreamAgent project and\npush them to its private GitHub repo. The commit gets its own entry in\nthe project's session history and version history, so the user can\nrestore/revert to it in the DreamAgent dashboard.\n\nUse it to (a) commit several MCP writes/deletes as ONE version — write\nand delete with auto_commit=false first — or (b) retry a commit after a\nfailure. Chat-driven edits commit automatically; this tool is for\ndirect file changes made through MCP.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"confirm": {
"type": "boolean",
"default": false,
"description": "must be true to execute"
},
"message": {
"type": "string",
"default": "",
"description": "short commit message, e.g. \"Update landing hero section\"\n(default \"MCP edit: project <id>\")"
},
"project_id": {
"type": "integer",
"description": "project to commit"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Version history of a DreamAgent project — recent commits (hash, message, status, timestamp) from its persistent commit log, newest first. Use it to review what changed and when; the user can restore any version from the DreamAgent dashboard version-history UI (mention the short hash so they can find it).
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| project_id * | integer |
{
"name": "dreamagent_list_commits",
"title": "List project version history",
"description": "Version history of a DreamAgent project — recent commits (hash,\nmessage, status, timestamp) from its persistent commit log, newest\nfirst. Use it to review what changed and when; the user can restore\nany version from the DreamAgent dashboard version-history UI (mention\nthe short hash so they can find it).",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"limit": {
"type": "integer",
"default": 10
},
"project_id": {
"type": "integer"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}WRITE ACTION — build & publish a DreamAgent project: rebuilds the app from the current source files and pushes the new version live. Use after finishing file edits (dreamagent_write_file) so the user's changes go live. Requires a paid plan. ASYNCHRONOUS: kick-off returns immediately; check dreamagent_get_project_status until the project reports 'ready'. confirm must be true to execute.
| Parameter | Type | Description |
|---|---|---|
| confirm | boolean | |
| project_id * | integer |
{
"name": "dreamagent_build_publish",
"title": "Build and publish project",
"description": "WRITE ACTION — build & publish a DreamAgent project: rebuilds the\napp from the current source files and pushes the new version live.\nUse after finishing file edits (dreamagent_write_file) so the user's\nchanges go live. Requires a paid plan.\n\nASYNCHRONOUS: kick-off returns immediately; check\ndreamagent_get_project_status until the project reports 'ready'.\nconfirm must be true to execute.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"confirm": {
"type": "boolean",
"default": false
},
"project_id": {
"type": "integer"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}WRITE ACTION — redesign a website project's UI to match a design image. Website projects only. The image (screenshot, mockup, or generated design) is the design spec; DreamAgent's AI reads it and redesigns the project's frontend to match it. confirm must be true to execute.
| Parameter | Type | Description |
|---|---|---|
| confirm | boolean | must be true to execute. |
| project_id * | integer | the website project to redesign. |
| image_base64 * | string | base64-encoded design reference image (PNG/JPG/WEBP). Send the actual image bytes verbatim — the image IS the spec. |
| instructions * | string | keep this SHORT — e.g. "Match this design image exactly." The image carries the design; do NOT write a long textual design spec duplicating what is visible in the image. Only add brief must-have requirements the image cannot show (e.g. "keep all existing pages and functionality", "Product Hunt view … |
{
"name": "dreamagent_design_mode",
"title": "Redesign UI from an image",
"description": "WRITE ACTION — redesign a website project's UI to match a design image.\nWebsite projects only.\n\nThe image (screenshot, mockup, or generated design) is the design\nspec; DreamAgent's AI reads it and redesigns the project's frontend\nto match it. confirm must be true to execute.",
"inputSchema": {
"type": "object",
"required": [
"project_id",
"image_base64",
"instructions"
],
"properties": {
"confirm": {
"type": "boolean",
"default": false,
"description": "must be true to execute."
},
"project_id": {
"type": "integer",
"description": "the website project to redesign."
},
"image_base64": {
"type": "string",
"description": "base64-encoded design reference image (PNG/JPG/WEBP).\nSend the actual image bytes verbatim — the image IS the spec."
},
"instructions": {
"type": "string",
"description": "keep this SHORT — e.g. \"Match this design image exactly.\"\nThe image carries the design; do NOT write a long textual design\nspec duplicating what is visible in the image. Only add brief\nmust-have requirements the image cannot show (e.g. \"keep all\nexisting pages and functionality\", \"Product Hunt view only\")."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}WRITE ACTION — creates a new DreamAgent project (website, Telegram bot, Discord bot, or AI agent). confirm must be true to execute. When several telegram/discord credentials are saved, the one to use is selected via bot_token_integration_id (see dreamagent_list_global_integrations). MODEL SELECTION — IMPORTANT: the default model is GLM 5.3 Flash ("z-ai/glm-5.3-flash"). Keep the default unless the USER explicitly asked for a specific model. Only pass a different id when the user named it, e.g. "use claude sonnet" → "anthropic/claude-sonnet-5.5", "use glm 5.3" → "z-ai/glm-5.3", "use opus" → "claude-opus-4-6". Claude models consume the project owner's Claude subscription quota — never choose them on your own initiative. CREATION IS ASYNCHRONOUS: after calling, check dreamagent_get_project_status repeatedly until the project is 'ready' or 'failed' (bots ~2-5 min, websites longer). CREDENTIALS: raw bot tokens are never accepted in chat or as inputs. For Telegram/Discord bots you MUST pass bot_token_integration_id — the ID of a saved credential from dreamagent_list_global_integrations. If none is saved, direct the user to dreamagent.cloud → Settings → Global Integrations. Other saved keys can be imported via global_integration_ids. Credentials are stored as project secrets and are never exposed back. DESCRIPTION = the refined creation brief describing WHAT should be built (see the structure notes below). THREE.JS / WEBGL SIGNAL: if the site genuinely needs real 3D/WebGL (3D scenes, games, product configurators, 3D visualization), the description MUST contain the exact word "three.js" (e.g. "Includes interactive 3D scenes built with three.js") — the platform installs the 3D stack based on that word. Include it ONLY when genuinely needed; regular websites must never include it. When included, also mention the 3D usage in one clause of the description. Create a concise but complete description of WHAT should be built: - product vision and target audience - user experience and core functionality - design/tone direction - important features and behavior - final expected result Do not include implementation details such as: - technology stack - architecture - database/API implementation - authentication implementation - deployment - CI/CD - testing commands Infer reasonable defaults when missing details are non-critical. Ask for clarification only when missing information materially affects the requested functionality, scope, credentials, or expected result. Prefer the following structure and constraints for each project type, but do not override explicit user requirements: Website: - Project Vision - Design Style - Pages - Hero Experience - Core Features - UI Components - Mobile Experience - Final Expectation - Prefer up to 4 pages unless the user clearly requires more. Telegram bot: - Bot Purpose - Commands - User Flow - Optional AI Features - Integrations when required - Final Expectations - Prefer a compact command set; always include /start and /help unless the user's explicit requirements conflict. Discord bot: - Bot Purpose - Slash Commands - Events - Permissions - Optional AI Features - Final Expectations - Prefer a compact command set; include /help where appropriate. Agent (recurring/scheduled automation with OAuth actions): - Purpose (what it monitors or automates) - Data Sources (which connected OAuth services: YouTube, GitHub, Discord, Notion, X, Google Sheets, Slack — or public APIs) - Schedule (e.g., every 5 minutes / hourly / daily at 9am) and/or Event Triggers (incoming webhook) - Conditions (when to act — thresholds, keywords, state changes) - Delivery Channels (Telegram, Discord, Slack, email — optional) - Final Expectation - Use concrete schedules; note that agents keep persistent state between runs and can call any connected OAuth integration. - Agents do NOT need a bot token unless they deliver via Telegram/ Discord (then a saved credential is required as for bots). SUPERPOWERS: the account m
Check a project's creation/deployment state. Terminal states are 'ready' (built and live) and 'failed'; while a project is being created it reports progressive phases such as 'creating', 'building', 'deploying', or 'ai_provisioning' — treat any non-terminal status as still building. Use after dreamagent_create_project (poll until ready or failed) and whenever the user asks whether a project is ready or live. NOTE: this reports the PROJECT's build/deploy state — NOT AI edit progress. For edits use dreamagent_get_edit_progress.
| Parameter | Type | Description |
|---|---|---|
| project_id * | integer | the project to check. |
{
"name": "dreamagent_get_project_status",
"title": "Get project status",
"description": "Check a project's creation/deployment state. Terminal states are\n'ready' (built and live) and 'failed'; while a project is being\ncreated it reports progressive phases such as 'creating',\n'building', 'deploying', or 'ai_provisioning' — treat any\nnon-terminal status as still building. Use after\ndreamagent_create_project (poll until ready or failed) and\nwhenever the user asks whether a project is ready or live.\n\nNOTE: this reports the PROJECT's build/deploy state — NOT AI edit\nprogress. For edits use dreamagent_get_edit_progress.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"project_id": {
"type": "integer",
"description": "the project to check."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}WRITE ACTION — builds, modifies, or fixes an EXISTING project with a natural-language instruction. Use ONLY when the user clearly asks for a change ("add X", "fix Y", "change the theme"). If the user is only asking for advice, analysis, review, or suggestions ("what could be improved?", "review my bot"), do NOT call this — answer from the project's info instead; a review request is not an edit. Describe ONLY the desired change — DreamAgent's AI automatically handles code, tests, rebuild, and redeployment. Completed changes are saved and committed automatically. ASYNCHRONOUS: returns immediately with the session_key; monitor with dreamagent_get_edit_progress (or dreamagent_get_chat_status with the returned session key) until a terminal state. A run has succeeded only once run_status reaches 'completed'. Each edit consumes AI usage from the account's plan. ERRORS: failures are returned as tool errors. If the edit was rejected before starting, the message says 'the edit was NOT started' plus the reason — HTTP 402 insufficient usage allowance, 409 another edit already active, 423 session lock held by another session, 404 wrong project id, 401 no account connected. ONE EDIT AT A TIME: the API rejects a second concurrent edit on the same project (409); check progress and wait for the current edit. SUPERPOWERS: projects can use the account's enabled add-on AI tools. To add or use one, name the feature in the message — DreamAgent's agent knows the enabled tools and wires the integration, UI and job handling automatically. Check the catalog with dreamagent_list_superpowers; disabled tools are enabled at dreamagent.cloud → Superpowers.
| Parameter | Type | Description |
|---|---|---|
| message * | string | the desired change (what + any behavioral constraints). |
| project_id * | integer | the project to modify. |
| new_session | boolean | optional — start a fresh session for a new topic. |
| session_key |
List a project's development sessions (conversation threads). Returns each session's identifier (session key) and context so you can select, continue, or monitor a specific development session — pass the session key to dreamagent_chat to continue that thread or to dreamagent_get_chat_status to monitor it. The session key is a reference used to address a session; it is not an authentication credential or a secret.
| Parameter | Type | Description |
|---|---|---|
| project_id * | integer | the project. |
{
"name": "dreamagent_list_sessions",
"title": "List project chat sessions",
"description": "List a project's development sessions (conversation threads).\nReturns each session's identifier (session key) and context so you\ncan select, continue, or monitor a specific development session —\npass the session key to dreamagent_chat to continue that thread or\nto dreamagent_get_chat_status to monitor it. The session key is a\nreference used to address a session; it is not an authentication\ncredential or a secret.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"project_id": {
"type": "integer",
"description": "the project."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Create a new development session for a project — a separate conversation with its own context. Use when the user wants to start a distinct development topic. A new session does NOT replace or affect the existing project — earlier sessions remain available.
| Parameter | Type | Description |
|---|---|---|
| label | string | optional name for the session. |
| project_id * | integer | the project. |
{
"name": "dreamagent_create_session",
"title": "Create a chat session",
"description": "Create a new development session for a project — a separate\nconversation with its own context. Use when the user wants to start\na distinct development topic. A new session does NOT replace or\naffect the existing project — earlier sessions remain available.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"label": {
"type": "string",
"default": "ChatGPT",
"description": "optional name for the session."
},
"project_id": {
"type": "integer",
"description": "the project."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}RECOVERY-ONLY — releases a project's editing lock when a stale or abandoned session blocks new modifications. NOT a normal editing step, and NEVER a way to bypass an actively running edit. The lock state is not machine-readable from here: to judge staleness, check dreamagent_get_edit_progress — if no edit is active but dreamagent_chat still fails with a lock error, the lock is stale. Confirm with the user before releasing if they may have the project open elsewhere.
| Parameter | Type | Description |
|---|---|---|
| project_id * | integer | the project to unlock. |
{
"name": "dreamagent_release_project_lock",
"title": "Release the project lock",
"description": "RECOVERY-ONLY — releases a project's editing lock when a stale or\nabandoned session blocks new modifications. NOT a normal editing\nstep, and NEVER a way to bypass an actively running edit.\n\nThe lock state is not machine-readable from here: to judge staleness,\ncheck dreamagent_get_edit_progress — if no edit is active but\ndreamagent_chat still fails with a lock error, the lock is stale.\nConfirm with the user before releasing if they may have the project\nopen elsewhere.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"project_id": {
"type": "integer",
"description": "the project to unlock."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Check the progress and final status of a specific AI development session using its session key. Use this to monitor an asynchronous edit until it completes, fails, or is cancelled — keep checking until a terminal state. The session key comes from dreamagent_chat or dreamagent_list_sessions and is an identifier, not a secret. Returns (actual fields): 'active=', 'run_status=', 'next_after=' (cursor for the next check), optional 'new_output:' (text produced since the last check), then either "Still working — poll again" or a terminal 'done=true' line: finished (with the final output tail), 'the edit was NOT started: <reason>' (rejected early, e.g. HTTP 402 insufficient credits), or 'stream error' (the connection to the run broke — the server-side run may still have finished; verify with dreamagent_get_edit_progress). run_status values: queued | running | cancel_requested | completed | failed | cancelled | interrupted | unknown.
| Parameter | Type | Description |
|---|---|---|
| after | integer | cursor from the previous check (0 on the first check). |
| session_key * | string | the session key returned by dreamagent_chat. |
{
"name": "dreamagent_get_chat_status",
"title": "Get chat status",
"description": "Check the progress and final status of a specific AI development\nsession using its session key. Use this to monitor an asynchronous\nedit until it completes, fails, or is cancelled — keep checking\nuntil a terminal state. The session key comes from dreamagent_chat\nor dreamagent_list_sessions and is an identifier, not a secret.\n\nReturns (actual fields): 'active=', 'run_status=', 'next_after='\n(cursor for the next check), optional 'new_output:' (text produced\nsince the last check), then either \"Still working — poll again\" or\na terminal 'done=true' line: finished (with the final output tail),\n'the edit was NOT started: <reason>' (rejected early, e.g. HTTP 402\ninsufficient credits), or 'stream error' (the connection to the run\nbroke — the server-side run may still have finished; verify with\ndreamagent_get_edit_progress).\nrun_status values: queued | running | cancel_requested | completed |\nfailed | cancelled | interrupted | unknown.",
"inputSchema": {
"type": "object",
"required": [
"session_key"
],
"properties": {
"after": {
"type": "integer",
"default": 0,
"description": "cursor from the previous check (0 on the first check)."
},
"session_key": {
"type": "string",
"description": "the session key returned by dreamagent_chat."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Check the latest AI edit progress for a project using its project identifier — no session key needed: the project id retrieves the session holding the latest edit. Use when the user asks whether their edit is finished, when the session key isn't available (e.g. a new conversation), and BEFORE starting any new edit. Returns (actual fields): 'session_key=' (the identifier of the session this progress comes from), 'edit_active=', 'run_status=', 'chunks=' (output size so far), optional 'recent_output (tail):', and a terminal 'result:' line: finished (with the final output tail), 'the edit was NOT started: <reason>' (rejected early, e.g. HTTP 402 insufficient credits), 'stream error', or 'no run is currently active'. run_status values: queued | running | cancel_requested | completed | failed | cancelled | interrupted | unknown. Distinct from dreamagent_get_project_status: project status = creation/deployment state (creating/ready/failed); edit progress = current AI modification state; chat status (dreamagent_get_chat_status) monitors one specific session by its session key. If edit_active is true, do NOT launch another edit for the same project.
| Parameter | Type | Description |
|---|---|---|
| project_id * | integer | the project being edited. |
{
"name": "dreamagent_get_edit_progress",
"title": "Get edit progress",
"description": "Check the latest AI edit progress for a project using its project\nidentifier — no session key needed: the project id retrieves the\nsession holding the latest edit. Use when the user asks whether\ntheir edit is finished, when the session key isn't available\n(e.g. a new conversation), and BEFORE starting any new edit.\n\nReturns (actual fields): 'session_key=' (the identifier of the\nsession this progress comes from), 'edit_active=', 'run_status=',\n'chunks=' (output size so far), optional 'recent_output (tail):',\nand a terminal 'result:' line: finished (with the final output\ntail), 'the edit was NOT started: <reason>' (rejected early,\ne.g. HTTP 402 insufficient credits), 'stream error', or 'no run is\ncurrently active'.\nrun_status values: queued | running | cancel_requested | completed |\nfailed | cancelled | interrupted | unknown.\n\nDistinct from dreamagent_get_project_status: project status =\ncreation/deployment state (creating/ready/failed); edit progress =\ncurrent AI modification state; chat status (dreamagent_get_chat_status)\nmonitors one specific session by its session key. If edit_active is\ntrue, do NOT launch another edit for the same project.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"project_id": {
"type": "integer",
"description": "the project being edited."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}DESTRUCTIVE — stops an AI edit that is currently running. Use ONLY when the user explicitly asks to stop/cancel the active edit. After cancellation, do NOT claim the requested change was completed — report that it was stopped. Returns 'Cancellation requested: <backend message>' — e.g. 'Query cancelled', 'Cancellation requested' (durable run), or 'No active query found'. Afterwards poll dreamagent_get_chat_status / dreamagent_get_edit_progress until run_status reports 'cancelled'.
| Parameter | Type | Description |
|---|---|---|
| session_key * | string | the session key of the running edit. |
{
"name": "dreamagent_cancel_chat",
"title": "Cancel the running chat",
"description": "DESTRUCTIVE — stops an AI edit that is currently running. Use ONLY\nwhen the user explicitly asks to stop/cancel the active edit.\nAfter cancellation, do NOT claim the requested change was\ncompleted — report that it was stopped.\n\nReturns 'Cancellation requested: <backend message>' — e.g. 'Query\ncancelled', 'Cancellation requested' (durable run), or 'No active\nquery found'. Afterwards poll dreamagent_get_chat_status /\ndreamagent_get_edit_progress until run_status reports 'cancelled'.",
"inputSchema": {
"type": "object",
"required": [
"session_key"
],
"properties": {
"session_key": {
"type": "string",
"description": "the session key of the running edit."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}WEBSITE PROJECTS ONLY — capture a screenshot of a DreamAgent-hosted page by URL: a deployed project's domain (e.g. my-app.dreamagent.cloud or a connected custom domain) or dreamagent.cloud itself. Best for checking a project's live pages after edits or deploys and reviewing layouts — returns the PNG as an MCP image content block PLUS a public URL. Non-DreamAgent URLs are rejected (this is enforced both here and by the host firewall). No project id needed — just the URL. Only public http(s) pages; private/internal hosts are rejected.
| Parameter | Type | Description |
|---|---|---|
| url * | string | absolute http(s) URL of the page to capture |
| width | integer | viewport width 320-1920 (default 1280) |
| height | integer | viewport height 240-2160 (default 800) |
{
"name": "dreamagent_screenshot_website",
"title": "Screenshot a website page",
"description": "WEBSITE PROJECTS ONLY — capture a screenshot of a DreamAgent-hosted\npage by URL: a deployed project's domain (e.g. my-app.dreamagent.cloud\nor a connected custom domain) or dreamagent.cloud itself. Best for\nchecking a project's live pages after edits or deploys and reviewing\nlayouts — returns the PNG as an MCP image content block PLUS a public\nURL. Non-DreamAgent URLs are rejected (this is enforced both here and\nby the host firewall).\n\nNo project id needed — just the URL. Only public http(s) pages;\nprivate/internal hosts are rejected.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "absolute http(s) URL of the page to capture"
},
"width": {
"type": "integer",
"default": 1280,
"description": "viewport width 320-1920 (default 1280)"
},
"height": {
"type": "integer",
"default": 800,
"description": "viewport height 240-2160 (default 800)"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}DreamAgent MCP server: create and manage projects (websites, Telegram bots, Discord bots, AI agents) on the user's DreamAgent account, edit project files, and apply changes to existing projects through DreamAgent's AI agent. Edits are asynchronous: chat, edit, build and create operations return immediately; poll their status with dreamagent_get_edit_progress, dreamagent_get_chat_status, or dreamagent_get_project_status until a terminal state. Raw bot tokens are never accepted as inputs — bots are created from saved credentials (see dreamagent_list_global_integrations). Write tools require confirm=true to execute.
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.
{
"name": "dreamagent_edit_file",
"title": "Edit a project file (find & replace)",
"description": "WRITE ACTION — make SMALL targeted changes to an EXISTING file in a\nDreamAgent project via exact search/replace. PREFERRED over\ndreamagent_write_file for editing existing files: you send only the\nchanged fragments (never the whole file) — cheaper, immune to payload\nsize/safety blocks in the calling client, and cannot corrupt unchanged\ncode. Use dreamagent_write_file only to CREATE files or for full rewrites.\n\nRead the file first (dreamagent_read_file) and copy each 'find' text\nEXACTLY as it appears — whitespace and indentation must match. All edits\nare validated BEFORE anything is saved; if any 'find' fails to match,\nthe file is left untouched and the error tells you which edit and why.",
"inputSchema": {
"type": "object",
"required": [
"project_id",
"file_path",
"edits"
],
"properties": {
"edits": {
"type": "array",
"items": {},
"description": "list of edit objects:\n{\"find\": \"<exact existing text>\",\n \"replace\": \"<new text>\",\n \"all\": false} # optional: replace every occurrence"
},
"confirm": {
"type": "boolean",
"default": false,
"description": "must be true to execute."
},
"file_path": {
"type": "string",
"description": "project-relative path of the EXISTING file to edit."
},
"project_id": {
"type": "integer",
"description": "project containing the file."
},
"auto_commit": {
"type": "boolean",
"default": true,
"description": "commit+push and record version history after saving\n(default true; pass false to batch several edit_file calls and\nfinish with one dreamagent_commit_push)."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}| Parameter | Type | Description |
|---|---|---|
| name * | string | project name (max 30 chars; a public subdomain is auto-generated). |
| model | string | |
| confirm | boolean | must be true to execute. (A legacy repeat-call confirmation path exists but is disabled unless the server sets ALLOW_REPEAT_CALL_CONFIRM=1.) |
| env_vars | any | optional non-secret environment variables. |
| description | any | the build request (what + for whom + features/tone). |
| project_type * | string | website / telegrambot / discordbot / agent. |
| global_integration_ids | any | optional saved-key IDs to import as env vars. |
| bot_token_integration_id | any | REQUIRED for telegrambot & discordbot — saved-credential ID (see dreamagent_list_global_integrations). |
{
"name": "dreamagent_create_project",
"title": "Create a new project",
"description": "WRITE ACTION — creates a new DreamAgent project (website, Telegram\nbot, Discord bot, or AI agent). confirm must be true to execute.\n\nWhen several telegram/discord credentials are saved, the one to use\nis selected via bot_token_integration_id (see\ndreamagent_list_global_integrations).\n\nMODEL SELECTION — IMPORTANT: the default model is GLM 5.3 Flash\n(\"z-ai/glm-5.3-flash\"). Keep the default unless the USER explicitly\nasked for a specific model. Only pass a different id when the user\nnamed it, e.g. \"use claude sonnet\" → \"anthropic/claude-sonnet-5.5\",\n\"use glm 5.3\" → \"z-ai/glm-5.3\", \"use opus\" → \"claude-opus-4-6\".\nClaude models consume the project owner's Claude subscription quota\n— never choose them on your own initiative.\n\nCREATION IS ASYNCHRONOUS: after calling, check\ndreamagent_get_project_status repeatedly until the project is\n'ready' or 'failed' (bots ~2-5 min, websites longer).\n\nCREDENTIALS: raw bot tokens are never accepted in chat or as inputs.\nFor Telegram/Discord bots you MUST pass bot_token_integration_id —\nthe ID of a saved credential from dreamagent_list_global_integrations.\nIf none is saved, direct the user to dreamagent.cloud → Settings →\nGlobal Integrations. Other saved keys can be imported via\nglobal_integration_ids. Credentials are stored as project secrets\nand are never exposed back.\n\nDESCRIPTION = the refined creation brief describing WHAT should be\nbuilt (see the structure notes below).\n\nTHREE.JS / WEBGL SIGNAL: if the site genuinely needs real 3D/WebGL\n(3D scenes, games, product configurators, 3D visualization), the\ndescription MUST contain the exact word \"three.js\" (e.g. \"Includes\ninteractive 3D scenes built with three.js\") — the platform installs\nthe 3D stack based on that word. Include it ONLY when genuinely\nneeded; regular websites must never include it. When included, also\nmention the 3D usage in one clause of the description.\n\nCreate a concise but complete description of WHAT should be built:\n- product vision and target audience\n- user experience and core functionality\n- design/tone direction\n- important features and behavior\n- final expected result\n\nDo not include implementation details such as:\n- technology stack\n- architecture\n- database/API implementation\n- authentication implementation\n- deployment\n- CI/CD\n- testing commands\n\nInfer reasonable defaults when missing details are non-critical.\nAsk for clarification only when missing information materially\naffects the requested functionality, scope, credentials, or\nexpected result.\n\nPrefer the following structure and constraints for each project\ntype, but do not override explicit user requirements:\n\nWebsite:\n- Project Vision\n- Design Style\n- Pages\n- Hero Experience\n- Core Features\n- UI Components\n- Mobile Experience\n- Final Expectation\n- Prefer up to 4 pages unless the user clearly requires more.\n\nTelegram bot:\n- Bot Purpose\n- Commands\n- User Flow\n- Optional AI Features\n- Integrations when required\n- Final Expectations\n- Prefer a compact command set; always include /start and /help\n unless the user's explicit requirements conflict.\n\nDiscord bot:\n- Bot Purpose\n- Slash Commands\n- Events\n- Permissions\n- Optional AI Features\n- Final Expectations\n- Prefer a compact command set; include /help where appropriate.\n\nAgent (recurring/scheduled automation with OAuth actions):\n- Purpose (what it monitors or automates)\n- Data Sources (which connected OAuth services: YouTube, GitHub,\n Discord, Notion, X, Google Sheets, Slack — or public APIs)\n- Schedule (e.g., every 5 minutes / hourly / daily at 9am) and/or\n Event Triggers (incoming webhook)\n- Conditions (when to act — thresholds, keywords, state changes)\n- Delivery Channels (Telegram, Discord, Slack, email — optional)\n- Final Expectation\n- Use concrete schedules; note that agents keep persistent state\n between runs and can call any connected OAuth integration.\n- Agents do NOT need a bot token unless they deliver via Telegram/\n Discord (then a saved credential is required as for bots).\n\nSUPERPOWERS: the account m",
"inputSchema": {
"type": "object",
"required": [
"name",
"project_type"
],
"properties": {
"name": {
"type": "string",
"description": "project name (max 30 chars; a public subdomain is auto-generated)."
},
"model": {
"type": "string",
"default": "z-ai/glm-5.3-flash"
},
"confirm": {
"type": "boolean",
"default": false,
"description": "must be true to execute. (A legacy repeat-call\nconfirmation path exists but is disabled unless the server\nsets ALLOW_REPEAT_CALL_CONFIRM=1.)"
},
"env_vars": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"default": null,
"description": "optional non-secret environment variables."
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "the build request (what + for whom + features/tone)."
},
"project_type": {
"type": "string",
"description": "website / telegrambot / discordbot / agent."
},
"global_integration_ids": {
"anyOf": [
{
"type": "array",
"items": {}
},
{
"type": "null"
}
],
"default": null,
"description": "optional saved-key IDs to import as env vars."
},
"bot_token_integration_id": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "REQUIRED for telegrambot & discordbot —\nsaved-credential ID (see dreamagent_list_global_integrations)."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}| any |
| optional — continue a specific development session. |
{
"name": "dreamagent_chat",
"title": "Chat with the project agent",
"description": "WRITE ACTION — builds, modifies, or fixes an EXISTING project with\na natural-language instruction. Use ONLY when the user clearly asks\nfor a change (\"add X\", \"fix Y\", \"change the theme\"). If the user is\nonly asking for advice, analysis, review, or suggestions (\"what\ncould be improved?\", \"review my bot\"), do NOT call this — answer\nfrom the project's info instead; a review request is not an edit.\n\nDescribe ONLY the desired change — DreamAgent's AI automatically\nhandles code, tests, rebuild, and redeployment. Completed changes\nare saved and committed automatically.\n\nASYNCHRONOUS: returns immediately with the session_key; monitor\nwith dreamagent_get_edit_progress (or dreamagent_get_chat_status\nwith the returned session key) until a terminal state. A run has\nsucceeded only once run_status reaches 'completed'. Each edit\nconsumes AI usage from the account's plan.\n\nERRORS: failures are returned as tool errors. If the edit was\nrejected before starting, the message says 'the edit was NOT\nstarted' plus the reason — HTTP 402 insufficient usage allowance,\n409 another edit already active, 423 session lock held by another\nsession, 404 wrong project id, 401 no account connected.\n\nONE EDIT AT A TIME: the API rejects a second concurrent edit on the\nsame project (409); check progress and wait for the current edit.\n\nSUPERPOWERS: projects can use the account's enabled add-on AI\ntools. To add or use one, name the feature in the message —\nDreamAgent's agent knows the enabled tools and wires the\nintegration, UI and job handling automatically. Check the catalog\nwith dreamagent_list_superpowers; disabled tools are enabled at\ndreamagent.cloud → Superpowers.",
"inputSchema": {
"type": "object",
"required": [
"project_id",
"message"
],
"properties": {
"message": {
"type": "string",
"description": "the desired change (what + any behavioral constraints)."
},
"project_id": {
"type": "integer",
"description": "the project to modify."
},
"new_session": {
"type": "boolean",
"default": false,
"description": "optional — start a fresh session for a new topic."
},
"session_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "optional — continue a specific development session."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"result"
],
"properties": {
"result": {
"type": "string"
}
},
"x-fastmcp-wrap-result": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}