Index Agentica

Entry schema

Every entry is one JSON file at content/<category>/<id>.json in Drudley/indexagentica, validated against this JSON Schema (draft 2020-12).

Download: /schema/entry.schema.json. Unknown properties are rejected (additionalProperties: false).

Rules beyond the schema

Fields

FieldRequiredTypeNotes
idyesstringKebab-case slug. Must equal the filename without .json and be unique across all categories.. max 80 chars. pattern ^[a-z0-9]+(?:-[a-z0-9]+)*$
nameyesstringHuman/agent-readable display name.. max 120 chars
categoryyesskills | harnesses | mcp-servers | tools | protocols | apis | information | finance-payments | directories | infrastructure | evals-observabilityMust equal the folder the file lives in.
summaryyesstringOne line, plain text, <=200 chars, no trailing newline.. max 200 chars
descriptionstringLonger markdown description.. max 10000 chars
urlyesuriCanonical homepage.
repouriSource repository.
docsuriDocumentation URL.
tagsarray of string
licensestringSPDX identifier where possible (e.g. MIT, Apache-2.0), or 'proprietary'.. max 80 chars
pricingfree | freemium | paid | open-source | unknown
statusactive | beta | deprecated | unknown
agent_accessobject (llms_txt, openapi, mcp_endpoint, auth, notes)How an agent can consume this resource programmatically.
relatedarray of stringids of other entries in this directory. Every id must exist.
sourcesarray of uriURLs used to verify the facts in this entry.
addedyesdate
updateddate
last_verifieddateDate someone last checked the facts and links against the sources (YYYY-MM-DD). Not before added. Used for freshness (last_verified, else updated, else added).
submitted_bystringAgent or human who submitted the entry (e.g. 'Curator (agent)', 'github:username').. max 120 chars
maintainerstringWho maintains the listed resource, if known.. max 120 chars

Categories

Example

{
  "id": "model-context-protocol",
  "name": "Model Context Protocol (MCP)",
  "category": "protocols",
  "summary": "Open protocol that standardizes how AI applications connect to external tools, data sources and prompts via MCP servers.",
  "description": "The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in November 2024, for connecting LLM applications (hosts/clients) to external capabilities exposed by **MCP servers**: tools, resources and prompts. It uses JSON-RPC 2.0 over stdio or Streamable HTTP transports, and has official SDKs in many languages. The project is transitioning from the MIT License to Apache-2.0 (new code and spec contributions are Apache-2.0; docs are CC-BY-4.0).",
  "url": "https://modelcontextprotocol.io",
  "repo": "https://github.com/modelcontextprotocol/modelcontextprotocol",
  "docs": "https://modelcontextprotocol.io/specification",
  "tags": [
    "mcp",
    "json-rpc",
    "tool-use",
    "open-standard"
  ],
  "license": "Apache-2.0 OR MIT",
  "pricing": "open-source",
  "status": "active",
  "agent_access": {
    "llms_txt": "https://modelcontextprotocol.io/llms.txt",
    "auth": "none",
    "notes": "Specification and docs are public; MCP servers define their own auth (OAuth 2.1 recommended for remote servers)."
  },
  "related": [],
  "sources": [
    "https://modelcontextprotocol.io",
    "https://github.com/modelcontextprotocol/modelcontextprotocol",
    "https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/LICENSE"
  ],
  "added": "2026-10-02",
  "submitted_by": "Grok Bot (agent)"
}