Agentic Web Wiki — standards reference, probe, validate, template is an MCP server published by wiki.agenticweb, hosted at agenticweb.wiki. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 13 tools, including define, get, compare, search, instances.
Look up 133 agentic-web standards, live-probe any domain, validate manifests, generate boilerplate.
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.
Define an agentic-web glossary term or standard by id, name, or alias. Returns { kind, id, name, definition_md, related_protocols, url } (plus standard_id/standard_summary_md when linked, or nearest-term hints on unknown-term error). Use define for concept definitions; use get when you need a standard's full specification record, or search for keyword discovery.
| Parameter | Type | Description |
|---|---|---|
| term * | string | glossary term id, name, or alias (e.g. agentic-web, agent card, MCP, x402) |
{
"name": "define",
"title": "Define a term",
"description": "Define an agentic-web glossary term or standard by id, name, or alias. Returns { kind, id, name, definition_md, related_protocols, url } (plus standard_id/standard_summary_md when linked, or nearest-term hints on unknown-term error). Use define for concept definitions; use get when you need a standard's full specification record, or search for keyword discovery.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"term"
],
"properties": {
"term": {
"type": "string",
"maxLength": 80,
"minLength": 1,
"description": "glossary term id, name, or alias (e.g. agentic-web, agent card, MCP, x402)"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Fetch one standard's complete specification record by id, acronym, filename, or RFC number. Returns verified v0.5 fields (v05_infobox_rows, v05_identity_sentence_md, v05_lead_md, v05_problem_md, v05_counterparts, v05_see_also, v05_wire_artifact, v05_last_checked_display), 6-domain bucket (domain), url, probe_rule, has_template, freshness, and evidence. Use get for one standard; compare for two specs or classic bridges; instances for implementations.
| Parameter | Type | Description |
|---|---|---|
| id * | string | standard id, acronym, filename, or RFC number (e.g. mcp, ard, llms.txt, RFC 9421) |
{
"name": "get",
"title": "Get a standard",
"description": "Fetch one standard's complete specification record by id, acronym, filename, or RFC number. Returns verified v0.5 fields (v05_infobox_rows, v05_identity_sentence_md, v05_lead_md, v05_problem_md, v05_counterparts, v05_see_also, v05_wire_artifact, v05_last_checked_display), 6-domain bucket (domain), url, probe_rule, has_template, freshness, and evidence. Use get for one standard; compare for two specs or classic bridges; instances for implementations.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "standard id, acronym, filename, or RFC number (e.g. mcp, ard, llms.txt, RFC 9421)"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Compare two standards, classic-to-agentic web bridges (openapi vs mcp, sitemap.xml vs llms.txt), or vendor conventions (AGENTS.md vs CLAUDE.md/GEMINI.md/.cursorrules). Returns { curated_comparison, relation_kind, relationship, verdict, domain_context, a, b, agentic_peers, comparison_url, adoption_note, license }. Uncurated pairs return verified definitions and 6-domain context without invented prose. Call instances({protocol}) for verified implementations.
| Parameter | Type | Description |
|---|---|---|
| a * | string | first standard id, acronym, or name |
| b * | string | second standard id, acronym, or name |
{
"name": "compare",
"title": "Compare two standards",
"description": "Compare two standards, classic-to-agentic web bridges (openapi vs mcp, sitemap.xml vs llms.txt), or vendor conventions (AGENTS.md vs CLAUDE.md/GEMINI.md/.cursorrules). Returns { curated_comparison, relation_kind, relationship, verdict, domain_context, a, b, agentic_peers, comparison_url, adoption_note, license }. Uncurated pairs return verified definitions and 6-domain context without invented prose. Call instances({protocol}) for verified implementations.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"a",
"b"
],
"properties": {
"a": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "first standard id, acronym, or name"
},
"b": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "second standard id, acronym, or name"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Search 132 standards and 52 glossary terms by keyword, acronym, alias, or 'A vs B' pair (pass q or alias query, 2–200 chars). Returns { results (top 10 ranked by title/alias/body match), matching_terms, comparison_url (when a curated comparison page exists for the top pair), next_steps } or nearest_ids/nearest_terms hints when empty. Use search for keyword discovery; use get for an exact id or ask for stack recommendations.
| Parameter | Type | Description |
|---|---|---|
| q | string | search query or comparison (e.g. agent discovery, A2A vs MCP, accept payments) |
| query | string | alias for q: search query or comparison |
{
"name": "search",
"title": "Search standards",
"description": "Search 132 standards and 52 glossary terms by keyword, acronym, alias, or 'A vs B' pair (pass q or alias query, 2–200 chars). Returns { results (top 10 ranked by title/alias/body match), matching_terms, comparison_url (when a curated comparison page exists for the top pair), next_steps } or nearest_ids/nearest_terms hints when empty. Use search for keyword discovery; use get for an exact id or ask for stack recommendations.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"q": {
"type": "string",
"maxLength": 200,
"minLength": 2,
"description": "search query or comparison (e.g. agent discovery, A2A vs MCP, accept payments)"
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 2,
"description": "alias for q: search query or comparison"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List observed implementations from the instances index. Optional filters: protocol (id or alias), type (origin, harness, sdk, venue, authority, agent), archetype, org (org_id), q (substring), limit (1–20, default 10). Returns { matched, returned, license, items } with id, org_id, name, type, url, implements, archetypes, observed, note, source, and implementations (protocol_id, role, support_level, probe_mode, status, checked_on; narrowed to the requested protocol when one was given).
| Parameter | Type | Description |
|---|---|---|
| q | string | case-insensitive substring over id, name, org_id, and note |
| org | string | org_id of the publishing organization |
| type | string | instance type: origin, harness, sdk, venue, authority, or agent |
| limit | integer | maximum items to return (1–20, default 10) |
| protocol | string | protocol id or alias; narrows items and their implementations |
| archetype | string | archetype slug matched against archetypes[] |
{
"name": "instances",
"title": "List observed implementations",
"description": "List observed implementations from the instances index. Optional filters: protocol (id or alias), type (origin, harness, sdk, venue, authority, agent), archetype, org (org_id), q (substring), limit (1–20, default 10). Returns { matched, returned, license, items } with id, org_id, name, type, url, implements, archetypes, observed, note, source, and implementations (protocol_id, role, support_level, probe_mode, status, checked_on; narrowed to the requested protocol when one was given).",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"q": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "case-insensitive substring over id, name, org_id, and note"
},
"org": {
"type": "string",
"maxLength": 80,
"minLength": 1,
"description": "org_id of the publishing organization"
},
"type": {
"enum": [
"origin",
"harness",
"sdk",
"venue",
"authority",
"agent"
],
"type": "string",
"description": "instance type: origin, harness, sdk, venue, authority, or agent"
},
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "maximum items to return (1–20, default 10)"
},
"protocol": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "protocol id or alias; narrows items and their implementations"
},
"archetype": {
"type": "string",
"maxLength": 80,
"minLength": 1,
"description": "archetype slug matched against archetypes[]"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}[TEMPORARILY PAUSED — use offline validate_manifest(id, content) instead] Check one public origin over HTTPS for a single standard or manifest (rate-limited to 120/min when live probing is active; see /status/). Returns { origin, id, found, outcome, status, url, reason, article }. Use has for a fast single-file check; use probe to evaluate all 37 protocol probe rules at once, or validate_manifest for per-manifest spec validation.
| Parameter | Type | Description |
|---|---|---|
| id * | string | probed standard id or filename (e.g. ard, llms-txt, mcp-server-cards, robots.txt) |
| origin * | string | public hostname to check (e.g. agenticweb.wiki, cloudflare.com) |
{
"name": "has",
"title": "Check an origin for one standard",
"description": "[TEMPORARILY PAUSED — use offline validate_manifest(id, content) instead] Check one public origin over HTTPS for a single standard or manifest (rate-limited to 120/min when live probing is active; see /status/). Returns { origin, id, found, outcome, status, url, reason, article }. Use has for a fast single-file check; use probe to evaluate all 37 protocol probe rules at once, or validate_manifest for per-manifest spec validation.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"origin",
"id"
],
"properties": {
"id": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "probed standard id or filename (e.g. ard, llms-txt, mcp-server-cards, robots.txt)"
},
"origin": {
"type": "string",
"maxLength": 253,
"minLength": 1,
"description": "public hostname to check (e.g. agenticweb.wiki, cloudflare.com)"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}[TEMPORARILY PAUSED — use offline validate_manifest(id, content) instead] Scan a public origin across 37 protocol probe rules covering 30 agent-facing paths and headers (24h KV packet cache with 7d report fallback; pass fresh: true to re-probe live with a 5-min per-origin cooldown, rate-limited to 30/min when live probing is active; see /status/). Returns { origin, checked, outcome, found_ids, found, absent, skipped, coverage, extracted, connect_recipe }; pass brief: true for found_ids + extracted endpoints only, compact: true to replace absent/skipped maps with absent_ids[], or verify: true to handshake MCP/A2A endpoints. Use probe for raw multi-path discovery; use has for one standard, or validate_manifest for per-manifest spec conformance.
| Parameter | Type | Description |
|---|---|---|
| id | string | optional single standard id or filename (e.g. ard, llms.txt) for a lean single-resource check |
| brief | boolean | true: return only found_ids, non-empty coverage, and key extracted resources |
| fresh | boolean | true: bypass the 24h KV cache and re-probe live (5-minute per-origin cooldown) |
| origin * | string | public hostname to probe across all 37 protocol rules and HTTP headers (e.g. agenticweb.wiki) |
| verify | boolean | true: actively handshake declared MCP (POST initialize) and A2A endpoints to verify liveness |
| compact | boolean | true: return absent_ids[] instead of full absent/skipped maps |
List machine-verified specification changes since a YYYY-MM-DD date or ISO-8601 timestamp (newest first, default 50, max 200). Returns { changes: [{ id, date, record_id, kind, field, from, to, claim, evidence_url, detector, commit }], total, since } filtered optionally by lifecycle step or record_id. Use changes for field-level spec diffs; use stale to audit unverified records or digest for ecosystem briefings.
| Parameter | Type | Description |
|---|---|---|
| step | string | optional lifecycle step filter (discover, identify, permit, read, act, coordinate, pay, present, account) |
| limit | integer | maximum number of change entries to return (default 50, max 200) |
| since * | string | YYYY-MM-DD or ISO-8601 timestamp |
| record_id | string | optional standard id or acronym to filter changes (e.g. mcp, a2a, x402) |
{
"name": "changes",
"title": "What changed since a date",
"description": "List machine-verified specification changes since a YYYY-MM-DD date or ISO-8601 timestamp (newest first, default 50, max 200). Returns { changes: [{ id, date, record_id, kind, field, from, to, claim, evidence_url, detector, commit }], total, since } filtered optionally by lifecycle step or record_id. Use changes for field-level spec diffs; use stale to audit unverified records or digest for ecosystem briefings.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"since"
],
"properties": {
"step": {
"enum": [
"discover",
"identify",
"permit",
"read",
"act",
"coordinate",
"pay",
"present",
"account"
],
"type": "string",
"description": "optional lifecycle step filter (discover, identify, permit, read, act, coordinate, pay, present, account)"
},
"limit": {
"type": "integer",
"maximum": 200,
"minimum": 1,
"description": "maximum number of change entries to return (default 50, max 200)"
},
"since": {
"type": "string",
"maxLength": 40,
"minLength": 10,
"description": "YYYY-MM-DD or ISO-8601 timestamp"
},
"record_id": {
"type": "string",
"maxLength": 80,
"description": "optional standard id or acronym to filter changes (e.g. mcp, a2a, x402)"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List standards whose last_verified date is older than N days (default 30), optionally filtered by lifecycle step. Returns { days, cutoff, total_standards, oldest_verified, newest_verified, records: [{ id, name, step, last_verified, freshness, url }] }. Use stale to audit verification freshness; use changes to inspect actual specification edits since a date.
| Parameter | Type | Description |
|---|---|---|
| days | integer | return standards whose last_verified date is older than this many days (default 30) |
| step | string | optional lifecycle step filter (discover, identify, permit, read, act, coordinate, pay, present, account) |
{
"name": "stale",
"title": "Stale records",
"description": "List standards whose last_verified date is older than N days (default 30), optionally filtered by lifecycle step. Returns { days, cutoff, total_standards, oldest_verified, newest_verified, records: [{ id, name, step, last_verified, freshness, url }] }. Use stale to audit verification freshness; use changes to inspect actual specification edits since a date.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"days": {
"type": "integer",
"maximum": 3650,
"minimum": 1,
"description": "return standards whose last_verified date is older than this many days (default 30)"
},
"step": {
"enum": [
"discover",
"identify",
"permit",
"read",
"act",
"coordinate",
"pay",
"present",
"account"
],
"type": "string",
"description": "optional lifecycle step filter (discover, identify, permit, read, act, coordinate, pay, present, account)"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Validate local manifest text in-memory before deploy (pass id + content, 120/min limit, no network fetch, always available) or audit a public origin across 12 syntax-validated manifests and 37 protocol probe rules when live probing is active (7d KV report cache; fresh: true re-probes live with 5-min cooldown, 30/min limit; see /status/). Returns { valid, errors, warnings, repaired_content } for single-file content checks, or { conformance_summary, agent_routing, connect_recipe, permissions, manifests } for origin audits; combine verify: true (live MCP/A2A handshakes), bridge: true (ARD/AI Catalog cross-manifest check), diff: true (manifest drift vs the previous KV cached report, or none when no snapshot is stored), or brief/compact payload trimming. Use validate_manifest for spec conformance and local linting; use probe for raw discovery or template to generate starter files.
| Parameter | Type | Description |
|---|---|---|
| id | string | manifest id or filename (ard, ai-catalog-well-known-file, mcp-server-cards, a2a, llms-txt, agents-md, anthropic-agent-skills-format, api-catalog-rfc9727, ai-crawler-tokens-robots, security-txt, auth-md, okf) |
| diff | boolean | true: compare the current report against the previous KV cached report, or none when no snapshot is stored (manifests_added/removed/changed, new_errors) |
| brief | boolean | true: return concise routing, callable endpoints, and permissions only |
| fresh | boolean | true: bypass the 7d KV report cache and re-probe live (5-minute per-origin cooldown) |
| bridge | boolean | true: fetch and validate each entry inside /.well-known/ard.json or ai-catalog.json against its target spec and check cross-manifest coherence |
Generate in-memory starter boilerplate for any of the 12 supported manifest ids (ard, ai-catalog-well-known-file [alias: ai-catalog], llms-txt, agents-md, anthropic-agent-skills-format [alias: agent-skills], mcp-server-cards, a2a, ai-crawler-tokens-robots, api-catalog-rfc9727, security-txt, auth-md, okf) without writing to disk. Returns { id, tier, maturity_note, target_path, content_type, recommended_headers, contents, edit_these, notes, spec_url, article, validate_with, filled_from }; when from_live: true is passed with domain, it probes the public origin over HTTPS to pre-fill discovered MCP, OpenAPI, A2A, and contact URLs. Use template to author a new manifest; use validate_manifest to lint existing content.
| Parameter | Type | Description |
|---|---|---|
| id * | string | one of ard, ai-catalog-well-known-file, llms-txt, agents-md, anthropic-agent-skills-format, mcp-server-cards, a2a, ai-crawler-tokens-robots, api-catalog-rfc9727, security-txt, auth-md, okf |
| name | string | service or project display name |
| domain | string | hostname, e.g. example.com |
| api_url | string | https URL of OpenAPI spec |
| contact | string | mailto:, https: or tel: URI |
| mcp_url | string | https URL of MCP endpoint |
| agent_url | string | https URL of A2A endpoint |
Match standards to an engineering goal (pass question/q and/or use_case + audience filters). Returns { question, matched_use_cases, standards (active matches: id, name, step, tier, lifecycle_status, phase, url), retired_or_superseded, avoid (alias of retired_or_superseded), comparisons }. Use ask to see which standards match a goal; use search for keyword lookup or get for one standard's record.
| Parameter | Type | Description |
|---|---|---|
| q | string | alias for question: natural-language implementation question |
| audience | string | target audience filter (site-owner, agent-builder, platform, standards-body) |
| question | string | natural-language implementation question (e.g. How do I accept payments from agents?) |
| use_case | string | optional explicit use-case id filter |
{
"name": "ask",
"title": "What should I implement?",
"description": "Match standards to an engineering goal (pass question/q and/or use_case + audience filters). Returns { question, matched_use_cases, standards (active matches: id, name, step, tier, lifecycle_status, phase, url), retired_or_superseded, avoid (alias of retired_or_superseded), comparisons }. Use ask to see which standards match a goal; use search for keyword lookup or get for one standard's record.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"q": {
"type": "string",
"maxLength": 200,
"minLength": 3,
"description": "alias for question: natural-language implementation question"
},
"audience": {
"enum": [
"site-owner",
"agent-builder",
"platform",
"standards-body"
],
"type": "string",
"description": "target audience filter (site-owner, agent-builder, platform, standards-body)"
},
"question": {
"type": "string",
"maxLength": 200,
"minLength": 3,
"description": "natural-language implementation question (e.g. How do I accept payments from agents?)"
},
"use_case": {
"enum": [
"discover-my-api",
"expose-tools-to-agents",
"let-agents-act-on-my-site",
"serve-content-to-agents",
"prove-agent-identity",
"delegate-user-authority",
"control-ai-crawling",
"accept-agent-payments",
"agent-checkout",
"agent-to-agent-messaging",
"agent-naming",
"render-agent-ui",
"audit-agent-actions",
"attribute-agent-traffic",
"describe-agent-capabilities"
],
"type": "string",
"description": "optional explicit use-case id filter"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Fetch the curated agentic-web standards and adoption digest for a YYYY-MM-DD date (defaults to latest; omits historical stats by default). Returns the stored digest items and sources plus latest_date and days_old (whole UTC days behind the newest digest; 0 when this date is the latest). Pass list: true to return { latest, latest_date, days_old: null, count, digests, page }, or include_stats: true (or compact: false; include_stats takes precedence when both are set) to include historical panel stats when present. Use digest for narrative briefings; use changes for raw field-level diffs.
| Parameter | Type | Description |
|---|---|---|
| date | string | YYYY-MM-DD or latest |
| list | boolean | true: list published dates |
| compact | boolean | true (default): omit historical stats block; pass false to include stats when include_stats is unset |
| include_stats | boolean | true: include historical stats block when present; false: omit stats (takes precedence over compact) |
{
"name": "digest",
"title": "Agentic web digest",
"description": "Fetch the curated agentic-web standards and adoption digest for a YYYY-MM-DD date (defaults to latest; omits historical stats by default). Returns the stored digest items and sources plus latest_date and days_old (whole UTC days behind the newest digest; 0 when this date is the latest). Pass list: true to return { latest, latest_date, days_old: null, count, digests, page }, or include_stats: true (or compact: false; include_stats takes precedence when both are set) to include historical panel stats when present. Use digest for narrative briefings; use changes for raw field-level diffs.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"date": {
"type": "string",
"maxLength": 40,
"description": "YYYY-MM-DD or latest"
},
"list": {
"type": "boolean",
"description": "true: list published dates"
},
"compact": {
"type": "boolean",
"description": "true (default): omit historical stats block; pass false to include stats when include_stats is unset"
},
"include_stats": {
"type": "boolean",
"description": "true: include historical stats block when present; false: omit stats (takes precedence over compact)"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Reference and manifest toolkit for 132 agentic-web standards across 6 domains. Call compare(a, b) for standard pairs, classic-to-agentic bridges (openapi vs mcp, sitemap.xml vs llms.txt), or AGENTS.md vs CLAUDE.md; get(id) for full cited specs; instances({protocol}) for verified implementations.
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": "probe",
"title": "Probe an origin",
"description": "[TEMPORARILY PAUSED — use offline validate_manifest(id, content) instead] Scan a public origin across 37 protocol probe rules covering 30 agent-facing paths and headers (24h KV packet cache with 7d report fallback; pass fresh: true to re-probe live with a 5-min per-origin cooldown, rate-limited to 30/min when live probing is active; see /status/). Returns { origin, checked, outcome, found_ids, found, absent, skipped, coverage, extracted, connect_recipe }; pass brief: true for found_ids + extracted endpoints only, compact: true to replace absent/skipped maps with absent_ids[], or verify: true to handshake MCP/A2A endpoints. Use probe for raw multi-path discovery; use has for one standard, or validate_manifest for per-manifest spec conformance.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"origin"
],
"properties": {
"id": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "optional single standard id or filename (e.g. ard, llms.txt) for a lean single-resource check"
},
"brief": {
"type": "boolean",
"description": "true: return only found_ids, non-empty coverage, and key extracted resources"
},
"fresh": {
"type": "boolean",
"description": "true: bypass the 24h KV cache and re-probe live (5-minute per-origin cooldown)"
},
"origin": {
"type": "string",
"maxLength": 253,
"minLength": 1,
"description": "public hostname to probe across all 37 protocol rules and HTTP headers (e.g. agenticweb.wiki)"
},
"verify": {
"type": "boolean",
"description": "true: actively handshake declared MCP (POST initialize) and A2A endpoints to verify liveness"
},
"compact": {
"type": "boolean",
"description": "true: return absent_ids[] instead of full absent/skipped maps"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}| origin | string | [TEMPORARILY PAUSED — pass id + content for offline validation instead] public hostname to fetch (optional when passing content + id for local pre-commit validation) |
| verify | boolean | true: actively handshake declared MCP and A2A endpoints and verify liveness |
| compact | boolean | true: omit nested probe packet and absent manifests |
| content | string | raw local JSON, Markdown, or text content to validate in-memory without network fetches |
| content_type | string | optional Content-Type header when validating local content |
{
"name": "validate_manifest",
"title": "Validate an origin's or local file's manifests",
"description": "Validate local manifest text in-memory before deploy (pass id + content, 120/min limit, no network fetch, always available) or audit a public origin across 12 syntax-validated manifests and 37 protocol probe rules when live probing is active (7d KV report cache; fresh: true re-probes live with 5-min cooldown, 30/min limit; see /status/). Returns { valid, errors, warnings, repaired_content } for single-file content checks, or { conformance_summary, agent_routing, connect_recipe, permissions, manifests } for origin audits; combine verify: true (live MCP/A2A handshakes), bridge: true (ARD/AI Catalog cross-manifest check), diff: true (manifest drift vs the previous KV cached report, or none when no snapshot is stored), or brief/compact payload trimming. Use validate_manifest for spec conformance and local linting; use probe for raw discovery or template to generate starter files.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"id": {
"type": "string",
"maxLength": 80,
"minLength": 1,
"description": "manifest id or filename (ard, ai-catalog-well-known-file, mcp-server-cards, a2a, llms-txt, agents-md, anthropic-agent-skills-format, api-catalog-rfc9727, ai-crawler-tokens-robots, security-txt, auth-md, okf)"
},
"diff": {
"type": "boolean",
"description": "true: compare the current report against the previous KV cached report, or none when no snapshot is stored (manifests_added/removed/changed, new_errors)"
},
"brief": {
"type": "boolean",
"description": "true: return concise routing, callable endpoints, and permissions only"
},
"fresh": {
"type": "boolean",
"description": "true: bypass the 7d KV report cache and re-probe live (5-minute per-origin cooldown)"
},
"bridge": {
"type": "boolean",
"description": "true: fetch and validate each entry inside /.well-known/ard.json or ai-catalog.json against its target spec and check cross-manifest coherence"
},
"origin": {
"type": "string",
"maxLength": 253,
"minLength": 1,
"description": "[TEMPORARILY PAUSED — pass id + content for offline validation instead] public hostname to fetch (optional when passing content + id for local pre-commit validation)"
},
"verify": {
"type": "boolean",
"description": "true: actively handshake declared MCP and A2A endpoints and verify liveness"
},
"compact": {
"type": "boolean",
"description": "true: omit nested probe packet and absent manifests"
},
"content": {
"type": "string",
"maxLength": 131072,
"description": "raw local JSON, Markdown, or text content to validate in-memory without network fetches"
},
"content_type": {
"type": "string",
"maxLength": 120,
"description": "optional Content-Type header when validating local content"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}| from_live |
| boolean |
| [TEMPORARILY PAUSED — omit from_live to generate offline boilerplate] true: probe domain live and pre-populate template URLs/metadata from its discovered endpoints |
| description | string | one-sentence description of the service or agent capability |
{
"name": "template",
"title": "Boilerplate for an agent-facing file",
"description": "Generate in-memory starter boilerplate for any of the 12 supported manifest ids (ard, ai-catalog-well-known-file [alias: ai-catalog], llms-txt, agents-md, anthropic-agent-skills-format [alias: agent-skills], mcp-server-cards, a2a, ai-crawler-tokens-robots, api-catalog-rfc9727, security-txt, auth-md, okf) without writing to disk. Returns { id, tier, maturity_note, target_path, content_type, recommended_headers, contents, edit_these, notes, spec_url, article, validate_with, filled_from }; when from_live: true is passed with domain, it probes the public origin over HTTPS to pre-fill discovered MCP, OpenAPI, A2A, and contact URLs. Use template to author a new manifest; use validate_manifest to lint existing content.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"maxLength": 60,
"minLength": 2,
"description": "one of ard, ai-catalog-well-known-file, llms-txt, agents-md, anthropic-agent-skills-format, mcp-server-cards, a2a, ai-crawler-tokens-robots, api-catalog-rfc9727, security-txt, auth-md, okf"
},
"name": {
"type": "string",
"maxLength": 100,
"description": "service or project display name"
},
"domain": {
"type": "string",
"maxLength": 253,
"description": "hostname, e.g. example.com"
},
"api_url": {
"type": "string",
"maxLength": 200,
"description": "https URL of OpenAPI spec"
},
"contact": {
"type": "string",
"maxLength": 200,
"description": "mailto:, https: or tel: URI"
},
"mcp_url": {
"type": "string",
"maxLength": 200,
"description": "https URL of MCP endpoint"
},
"agent_url": {
"type": "string",
"maxLength": 200,
"description": "https URL of A2A endpoint"
},
"from_live": {
"type": "boolean",
"description": "[TEMPORARILY PAUSED — omit from_live to generate offline boilerplate] true: probe domain live and pre-populate template URLs/metadata from its discovered endpoints"
},
"description": {
"type": "string",
"maxLength": 300,
"description": "one-sentence description of the service or agent capability"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}