Server definition
- Hash
- sha256:ae8315a649f6d6623daef0e832bb47cdfc42ccd1024d1ba7f1585e0f7fc0fd62
- What it is
- What a remote MCP server returned when asked what it offers: 8 tools
The blob, as servednamed by its sha256
{
"instructions": "News + CVE + government-document portal for AI agents. Three content families, filter by category prefix: news articles (category=\"news\"), CVE/vulnerability advisories (category=\"security\"), and government documents (category=\"government\"). Use portal_list to page item metadata (summaries, omission reasons, English search signals, entities), select what you need, then call portal_get for the bodies of only those items. List first, get only when needed. Use portal_search for BM25 full-text search over titles, summaries, sentence-free English search signals and (where the license allows) bodies; Japanese is morphologically segmented so it matches words a substring search would miss, and results carry score, rank and a snippet. For recurring monitoring, use portal_changes with its cursor; it returns only existing articles republished after a content_hash change, not initial creation or enrichment. A third family, the Agent-Readiness directory, rates other websites on how well they expose AI-agent surfaces (llms.txt, api-catalog, MCP server card, ...): browse it with portal_list_agent_surfaces and drill into one domain with portal_get_agent_surface.",
"tools": [
{
"description": "Return only articles whose existing content_hash changed and were republished.\n\nNew article creation and asynchronous enrichment changes are excluded. Save next_cursor\nand pass it on the next poll for stable, token-light incremental retrieval.",
"inputSchema": {
"properties": {
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Category"
},
"cursor": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Cursor"
},
"lang": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lang"
},
"limit": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Limit"
},
"since": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Since"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source"
}
},
"type": "object"
},
"name": "portal_changes",
"outputSchema": {
"additionalProperties": true,
"type": "object"
}
},
{
"description": "Fetch a full article by id.\n\nThe body/summary returned is gated by license_note:\n - full (default): body included\n - summary-only: no body, summary (summary/summary_en) present\n - link-only: link and metadata only, no summary or body\n\nArgs:\n id: article id (e.g. \"news-20260702-4c769f\")\n include_body: false to return metadata only, omitting the body (even when license is full)\n\nReturns:\n The article's full metadata + body (body_policy states which policy was applied).\n Returns {error: \"not_found\", id} if the article does not exist.",
"inputSchema": {
"properties": {
"id": {
"title": "Id",
"type": "string"
},
"include_body": {
"default": true,
"title": "Include Body",
"type": "boolean"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "portal_get",
"outputSchema": {
"additionalProperties": true,
"type": "object"
}
},
{
"description": "Fetch one website's full Agent-Readiness assessment by domain.\n\nArgs:\n domain: the site's domain (e.g. \"example.com\"). Normalized (scheme/path/case stripped).\n\nReturns:\n domain, score (0-100 overall), level, level_label, categories[] (per-category pct with\n passed/failed/neutral check ids), checks[] (every verified check with its HTTP status\n and byte size), llms_txt_url / llms_full_txt_url, discovered_via and\n first_seen_at / checked_at / updated_at timestamps.\n Returns {error: \"not_found\", domain} if the domain has not been scanned.",
"inputSchema": {
"properties": {
"domain": {
"title": "Domain",
"type": "string"
}
},
"required": [
"domain"
],
"type": "object"
},
"name": "portal_get_agent_surface",
"outputSchema": {
"additionalProperties": true,
"type": "object"
}
},
{
"description": "List item metadata (no body, token-light).\n\nTwo content families are distinguished by category prefix:\n - news articles: category=\"news\" (or narrower, e.g. \"news/world\")\n - CVE/vulnerability advisories: category=\"security\" (or \"security/library\" / \"security/os\" / \"security/app\")\nOmit category to list both together.\n\nArgs:\n category: category prefix match. e.g. \"news\" matches all news/*, \"security\" matches all CVE, \"news/world\" narrows it\n status: filter by ingested/processed/enriched/published (all if omitted)\n source: feed identifier. e.g. \"ghost-chinng-lab\"\n lang: original language. e.g. \"ja\"\n since: lower bound on published_at (ISO 8601. e.g. \"2026-07-01\")\n until: upper bound on published_at (ISO 8601)\n q: title substring search\n limit: number of results (default 20, max 100)\n offset: paging start position\n\nReturns:\n {total, count, limit, offset, items[]} — each item includes summary/summary_en/tags/\n entities/related_auto/license_note plus summary_omitted_reason, redistribution,\n keywords_en, entities_en, topics_en and numeric_facts, but **never the body**.",
"inputSchema": {
"properties": {
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Category"
},
"lang": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lang"
},
"limit": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Limit"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
},
"q": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Q"
},
"since": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Since"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source"
},
"status": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Status"
},
"until": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Until"
}
},
"type": "object"
},
"name": "portal_list",
"outputSchema": {
"additionalProperties": true,
"type": "object"
}
},
{
"description": "List scanned websites by their AI-agent readiness (the Agent-Readiness directory).\n\nA separate content family from news/CVE: each entry is a domain we actively scanned for\nagent-facing surfaces across five categories (Discoverability / Content / Bot Access\nControl / API-Auth-MCP-Skill / Commerce). Checks are graded like the Cloudflare\nAgent-Ready scanner: each category yields a percentage, and the overall score (0-100,\nCommerce excluded as informational) maps to Level 0-3 (0 Unprepared / 1 Agent-Curious /\n2 Agent-Aware / 3 Agent-Native). Only scanned domains with results are listed.\n\nArgs:\n level: filter to a single readiness level (0-3)\n min_score: only surfaces with overall score (0-100) >= this value\n discovered_via: candidate source filter. e.g. \"tranco\" / \"majestic\" / \"manual\"\n sort: \"score\" (default, highest readiness first) or \"recent\" (recently changed first, for level-up tracking)\n limit: number of results (default 20, max 100)\n offset: paging start position\n\nReturns:\n {total, count, limit, offset, items[]} — each item has domain, score (0-100), level,\n level_label, categories[] (per-category pct + pass/fail breakdown), checks[] (every\n check with its HTTP status), llms_txt_url, discovered_via and timestamps.",
"inputSchema": {
"properties": {
"discovered_via": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Discovered Via"
},
"level": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Level"
},
"limit": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Limit"
},
"min_score": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Min Score"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
},
"sort": {
"default": "score",
"title": "Sort",
"type": "string"
}
},
"type": "object"
},
"name": "portal_list_agent_surfaces",
"outputSchema": {
"additionalProperties": true,
"type": "object"
}
},
{
"description": "List official government documents without their Markdown bodies.\n\nUse country (for example \"us\", \"jp\", or \"eu\") and source to narrow results. Federal\nRegister document types include \"Rule\", \"Proposed Rule\", and \"Notice\"; Japanese\nRSS sources use their configured update class as document_type. EU sources cover\nEUR-Lex legislation and case-law (document_number carries the CELEX number) and\nEuropean Commission press releases.\nCall portal_get for a selected id when its full portal record is needed.",
"inputSchema": {
"properties": {
"country": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Country"
},
"document_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Document Type"
},
"limit": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Limit"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
},
"since": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Since"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source"
},
"until": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Until"
}
},
"type": "object"
},
"name": "portal_list_government",
"outputSchema": {
"additionalProperties": true,
"type": "object"
}
},
{
"description": "Return the most retrieved portal pages.\n\nArgs:\n window: rolling window such as \"24h\", \"7d\", \"30d\" or \"90d\".\n category: optional category prefix such as \"news\" or \"security\".\n limit: number of results (default 10, max 100 on the analytics service).",
"inputSchema": {
"properties": {
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Category"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"window": {
"default": "24h",
"title": "Window",
"type": "string"
}
},
"type": "object"
},
"name": "portal_popular",
"outputSchema": {
"additionalProperties": true,
"type": "object"
}
},
{
"description": "BM25 full-text search over items (no body returned, token-light).\n\nRanked by weighted BM25 (SQLite FTS5) over the title, the original-language summary,\nthe English summary, sentence-free English search signals and — for items whose\nlicense permits redistribution — the body.\nJapanese text is morphologically segmented at index time, so Japanese queries match\nwords that a substring search would miss. Results carry score (0-1), rank and a\nsnippet of the matching passage. Use portal_get to read a matched item's body.\n\nArgs:\n q: keyword(s). space-separated terms are ANDed. e.g. \"openai gpt\"\n category: category prefix match. e.g. \"news\" or \"security\"\n status: filter by ingested/processed/enriched/published (all if omitted)\n source: feed identifier. e.g. \"ghost-chinng-lab\"\n lang: original language. e.g. \"ja\"\n limit: number of results (default 20, max 100)\n offset: paging start position\n mode: \"bm25\" (default, relevance-ranked) or \"index\" (substring match, newest first)\n\nReturns:\n {total, count, limit, offset, query, mode, total_is_capped, items[]} — same\n license-gated item shape as portal_list (summary/summary_en and snippet omitted\n for link-only, omission reason and search signals retained), **never the body**.\n In bm25 mode each item adds score / rank /\n snippet, and total is an estimate capped for cost. If the BM25 index is not\n usable the call transparently falls back to mode \"index\" and reports why in\n degraded_reason.",
"inputSchema": {
"properties": {
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Category"
},
"lang": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lang"
},
"limit": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Limit"
},
"mode": {
"default": "bm25",
"title": "Mode",
"type": "string"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
},
"q": {
"title": "Q",
"type": "string"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source"
},
"status": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Status"
}
},
"required": [
"q"
],
"type": "object"
},
"name": "portal_search",
"outputSchema": {
"additionalProperties": true,
"type": "object"
}
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:ae8315a649f6d6623daef0e832bb47cdfc42ccd1024d1ba7f1585e0f7fc0fd62 | sha256sum