{ "type": "skill", "id": "indexagentica-lookup", "title": "Index Agentica lookup", "summary": "Query the Index Agentica directory (llms.txt, JSON API, per-entry JSON and markdown) to discover agent tools, MCP servers and APIs, and to propose new entries.", "author": "Agentica Author", "tags": [ "directory", "discovery", "llms-txt", "json-api" ], "published": "2026-10-02", "last_verified": "2026-10-02", "entries": [ "llms-txt", "model-context-protocol", "openapi" ], "links": { "html": "https://indexagentica.com/skills/indexagentica-lookup/", "markdown": "https://indexagentica.com/skills/indexagentica-lookup.md", "json": "https://indexagentica.com/api/longform/skills/indexagentica-lookup.json", "skill_md": "https://indexagentica.com/skills/indexagentica-lookup/SKILL.md", "zip": "https://indexagentica.com/skills/indexagentica-lookup.zip", "source": "https://github.com/Drudley/indexagentica/blob/main/content-long/skills/indexagentica-lookup/SKILL.md" }, "status": "published", "skill": { "name": "indexagentica-lookup", "description": "Search the Index Agentica directory of agent tools, MCP servers, APIs, protocols, skills, harnesses, sandboxes and payment rails through its static JSON API, llms.txt and per-entry markdown. Use when you need to find, shortlist or compare resources for building or extending an AI agent, look up a tool's MCP endpoint, docs or auth method, or suggest a missing entry.", "license": "MIT", "compatibility": "Needs HTTPS access to indexagentica.com. curl and jq are optional but make filtering easy. No auth or API key.", "version": "1.0", "files": [ { "path": "SKILL.md", "url": "https://indexagentica.com/skills/indexagentica-lookup/SKILL.md" } ], "skill_md": "https://indexagentica.com/skills/indexagentica-lookup/SKILL.md", "zip": "https://indexagentica.com/skills/indexagentica-lookup.zip" }, "entries_detail": [ { "id": "llms-txt", "name": "llms.txt", "summary": "Proposal to standardize a /llms.txt Markdown file that gives LLMs and agents a concise guide to a website's content.", "url": "https://indexagentica.com/entries/llms-txt/", "json": "https://indexagentica.com/api/entries/llms-txt.json" }, { "id": "model-context-protocol", "name": "Model Context Protocol (MCP)", "summary": "Open protocol that standardizes how AI applications connect to external tools, data sources and prompts via MCP servers.", "url": "https://indexagentica.com/entries/model-context-protocol/", "json": "https://indexagentica.com/api/entries/model-context-protocol.json" }, { "id": "openapi", "name": "OpenAPI Specification", "summary": "Language-agnostic standard for describing HTTP APIs, widely used to generate agent tools from API definitions.", "url": "https://indexagentica.com/entries/openapi/", "json": "https://indexagentica.com/api/entries/openapi.json" } ], "related": [ { "type": "guide", "id": "connect-an-agent-to-a-remote-mcp-server", "title": "Connect an agent to a remote MCP server", "url": "https://indexagentica.com/guides/connect-an-agent-to-a-remote-mcp-server/", "json": "https://indexagentica.com/api/longform/guides/connect-an-agent-to-a-remote-mcp-server.json" }, { "type": "skill", "id": "connect-remote-mcp", "title": "Connect a remote MCP server", "url": "https://indexagentica.com/skills/connect-remote-mcp/", "json": "https://indexagentica.com/api/longform/skills/connect-remote-mcp.json" } ], "sources": [ { "url": "https://indexagentica.com/agents/" }, { "url": "https://indexagentica.com/openapi.json" }, { "url": "https://indexagentica.com/api/index.json" }, { "url": "https://indexagentica.com/llms.txt" }, { "url": "https://indexagentica.com/contribute.json" }, { "url": "https://indexagentica.com/schema/entry.schema.json" } ], "front_matter": { "name": "indexagentica-lookup", "description": "Search the Index Agentica directory of agent tools, MCP servers, APIs, protocols, skills, harnesses, sandboxes and payment rails through its static JSON API, llms.txt and per-entry markdown. Use when you need to find, shortlist or compare resources for building or extending an AI agent, look up a tool's MCP endpoint, docs or auth method, or suggest a missing entry.", "license": "MIT", "compatibility": "Needs HTTPS access to indexagentica.com. curl and jq are optional but make filtering easy. No auth or API key.", "metadata": { "title": "Index Agentica lookup", "summary": "Query the Index Agentica directory (llms.txt, JSON API, per-entry JSON and markdown) to discover agent tools, MCP servers and APIs, and to propose new entries.", "author": "Agentica Author", "version": "1.0", "last_verified": "2026-10-02", "published": "2026-10-02", "tags": "directory, discovery, llms-txt, json-api", "entries": "llms-txt, model-context-protocol, openapi", "related": "connect-an-agent-to-a-remote-mcp-server, connect-remote-mcp", "sources": "https://indexagentica.com/agents/ https://indexagentica.com/openapi.json https://indexagentica.com/api/index.json https://indexagentica.com/llms.txt https://indexagentica.com/contribute.json https://indexagentica.com/schema/entry.schema.json" } }, "markdown": "\n# Index Agentica lookup\n\nIndex Agentica (https://indexagentica.com) is a static, agent-first directory with no auth, no JavaScript and open CORS. Crawling is explicitly allowed. Every entry is one JSON object validated against https://indexagentica.com/schema/entry.schema.json.\n\n## Pick the right endpoint\n\n| Need | Fetch | Size, notes |\n|---|---|---|\n| Skim everything cheaply | https://indexagentica.com/llms.txt | About 50 KB of markdown: one line per entry, grouped by category |\n| Everything in full, for context | https://indexagentica.com/llms-full.txt | About 220 KB, so only load it when you need it |\n| Structured search | https://indexagentica.com/api/index.json | About 340 KB JSON: `counts`, `categories[]`, `entries[]` |\n| One category | `https://indexagentica.com/api/.json` | Same shape, filtered. Has `category`, `count`, `entries[]` |\n| Category list | https://indexagentica.com/api/categories.json | Slugs, names, counts |\n| One entry | `https://indexagentica.com/api/entries/.json` or `https://indexagentica.com/entries/.md` | The `.md` version is the most compact for reading |\n| API description | https://indexagentica.com/openapi.json | OpenAPI 3.1 |\n\nCategory slugs: `skills`, `harnesses`, `mcp-servers`, `tools`, `protocols`, `apis`, `information`, `finance-payments`, `directories`, `infrastructure` (hosting and sandboxes), `evals-observability`.\n\nResponses are served with `cache-control: max-age=600` and an `ETag`. Cache them, and send `If-None-Match` when you refetch.\n\n## Entry fields you will use\n\n`id`, `name`, `category`, `summary` (one neutral line), `description` (markdown), `url`, `repo`, `docs`, `tags[]`, `license`, `pricing` (`free` / `freemium` / `paid` / `open-source` / `unknown`), `status` (`active` / `beta` / `deprecated` / `unknown`), `agent_access` (`llms_txt`, `openapi`, `mcp_endpoint`, `auth`, `notes`), `related[]` (other entry ids), `sources[]` (the URLs the facts were checked against), `last_verified`, and `links` (`html`, `markdown`, `json`). Optional fields are omitted when unverified. A missing field means unknown, not \"no\".\n\n## Recipes\n\nKeyword search over id, name, summary and tags:\n\n```bash\ncurl -s https://indexagentica.com/api/index.json | jq -r --arg q \"sandbox\" '\n .entries[] | select((.id+\" \"+.name+\" \"+.summary+\" \"+((.tags//[])|join(\" \"))) | ascii_downcase | contains($q))\n | \"\\(.id)\\t\\(.category)\\t\\(.url)\"'\n```\n\nEverything with a given tag:\n\n```bash\ncurl -s https://indexagentica.com/api/index.json | jq -r '.entries[] | select((.tags//[]) | index(\"x402\")) | \"\\(.id)\\t\\(.summary)\"'\n```\n\nRemote MCP servers and their auth method:\n\n```bash\ncurl -s https://indexagentica.com/api/index.json | jq -r '.entries[] | select(.agent_access.mcp_endpoint) | \"\\(.id)\\t\\(.agent_access.mcp_endpoint)\\t\\(.agent_access.auth // \"unknown\")\"'\n```\n\nRead one entry, then follow its `related` ids:\n\n```bash\ncurl -s https://indexagentica.com/entries/e2b.md\ncurl -s https://indexagentica.com/api/entries/e2b.json | jq -r '.related[]?'\n```\n\nWithout a shell, fetch `llms.txt`, find candidate ids in the relevant `## ` section, then fetch `/entries/.md` for each.\n\n## How to use results well\n\n- Shortlist from `summary`, then confirm against the entry's `docs` or `sources` before you recommend anything. The directory is a starting point, not the final authority. Check `last_verified`.\n- Prefer `status: active`. Flag `beta` and `deprecated` entries.\n- When the user wants something an agent can call directly, look at `agent_access` (MCP endpoint, OpenAPI, llms.txt, auth).\n- Cite entries by their `links.html` URL, `https://indexagentica.com/entries//`.\n\n## MCP server (when deployed)\n\nA read-only remote MCP server with `search(query, category?, tags?, limit?)`, `get_entry(id)` and `list_categories()` is planned at `https://mcp.indexagentica.com/mcp` (Streamable HTTP, no auth, about 120 requests per minute per IP). As of 2026-10-02 it is **not live**. Check `https://mcp.indexagentica.com/health` first and use the static API above if it doesn't respond.\n\n## Suggest a missing entry\n\nRead https://indexagentica.com/contribute.json for the rules and template. There are two paths, both merged by a human:\n\n1. A pull request adding `content//.json` to https://github.com/Drudley/indexagentica. Run `node scripts/validate.mjs` first.\n2. A \"New entry\" issue (title `[New entry]: `), using the issue body template in `contribute.json`.\n\nSummaries must be neutral (10-200 characters). List your verification URLs in `sources`, and say that you are an agent and who you act for. Only open an issue or PR when your user has asked you to.\n", "raw": "---\nname: indexagentica-lookup\ndescription: Search the Index Agentica directory of agent tools, MCP servers, APIs, protocols, skills, harnesses, sandboxes and payment rails through its static JSON API, llms.txt and per-entry markdown. Use when you need to find, shortlist or compare resources for building or extending an AI agent, look up a tool's MCP endpoint, docs or auth method, or suggest a missing entry.\nlicense: MIT\ncompatibility: Needs HTTPS access to indexagentica.com. curl and jq are optional but make filtering easy. No auth or API key.\nmetadata:\n title: Index Agentica lookup\n summary: Query the Index Agentica directory (llms.txt, JSON API, per-entry JSON and markdown) to discover agent tools, MCP servers and APIs, and to propose new entries.\n author: Agentica Author\n version: \"1.0\"\n last_verified: 2026-10-02\n published: 2026-10-02\n tags: directory, discovery, llms-txt, json-api\n entries: llms-txt, model-context-protocol, openapi\n related: connect-an-agent-to-a-remote-mcp-server, connect-remote-mcp\n sources: https://indexagentica.com/agents/ https://indexagentica.com/openapi.json https://indexagentica.com/api/index.json https://indexagentica.com/llms.txt https://indexagentica.com/contribute.json https://indexagentica.com/schema/entry.schema.json\n---\n\n# Index Agentica lookup\n\nIndex Agentica (https://indexagentica.com) is a static, agent-first directory with no auth, no JavaScript and open CORS. Crawling is explicitly allowed. Every entry is one JSON object validated against https://indexagentica.com/schema/entry.schema.json.\n\n## Pick the right endpoint\n\n| Need | Fetch | Size, notes |\n|---|---|---|\n| Skim everything cheaply | https://indexagentica.com/llms.txt | About 50 KB of markdown: one line per entry, grouped by category |\n| Everything in full, for context | https://indexagentica.com/llms-full.txt | About 220 KB, so only load it when you need it |\n| Structured search | https://indexagentica.com/api/index.json | About 340 KB JSON: `counts`, `categories[]`, `entries[]` |\n| One category | `https://indexagentica.com/api/.json` | Same shape, filtered. Has `category`, `count`, `entries[]` |\n| Category list | https://indexagentica.com/api/categories.json | Slugs, names, counts |\n| One entry | `https://indexagentica.com/api/entries/.json` or `https://indexagentica.com/entries/.md` | The `.md` version is the most compact for reading |\n| API description | https://indexagentica.com/openapi.json | OpenAPI 3.1 |\n\nCategory slugs: `skills`, `harnesses`, `mcp-servers`, `tools`, `protocols`, `apis`, `information`, `finance-payments`, `directories`, `infrastructure` (hosting and sandboxes), `evals-observability`.\n\nResponses are served with `cache-control: max-age=600` and an `ETag`. Cache them, and send `If-None-Match` when you refetch.\n\n## Entry fields you will use\n\n`id`, `name`, `category`, `summary` (one neutral line), `description` (markdown), `url`, `repo`, `docs`, `tags[]`, `license`, `pricing` (`free` / `freemium` / `paid` / `open-source` / `unknown`), `status` (`active` / `beta` / `deprecated` / `unknown`), `agent_access` (`llms_txt`, `openapi`, `mcp_endpoint`, `auth`, `notes`), `related[]` (other entry ids), `sources[]` (the URLs the facts were checked against), `last_verified`, and `links` (`html`, `markdown`, `json`). Optional fields are omitted when unverified. A missing field means unknown, not \"no\".\n\n## Recipes\n\nKeyword search over id, name, summary and tags:\n\n```bash\ncurl -s https://indexagentica.com/api/index.json | jq -r --arg q \"sandbox\" '\n .entries[] | select((.id+\" \"+.name+\" \"+.summary+\" \"+((.tags//[])|join(\" \"))) | ascii_downcase | contains($q))\n | \"\\(.id)\\t\\(.category)\\t\\(.url)\"'\n```\n\nEverything with a given tag:\n\n```bash\ncurl -s https://indexagentica.com/api/index.json | jq -r '.entries[] | select((.tags//[]) | index(\"x402\")) | \"\\(.id)\\t\\(.summary)\"'\n```\n\nRemote MCP servers and their auth method:\n\n```bash\ncurl -s https://indexagentica.com/api/index.json | jq -r '.entries[] | select(.agent_access.mcp_endpoint) | \"\\(.id)\\t\\(.agent_access.mcp_endpoint)\\t\\(.agent_access.auth // \"unknown\")\"'\n```\n\nRead one entry, then follow its `related` ids:\n\n```bash\ncurl -s https://indexagentica.com/entries/e2b.md\ncurl -s https://indexagentica.com/api/entries/e2b.json | jq -r '.related[]?'\n```\n\nWithout a shell, fetch `llms.txt`, find candidate ids in the relevant `## ` section, then fetch `/entries/.md` for each.\n\n## How to use results well\n\n- Shortlist from `summary`, then confirm against the entry's `docs` or `sources` before you recommend anything. The directory is a starting point, not the final authority. Check `last_verified`.\n- Prefer `status: active`. Flag `beta` and `deprecated` entries.\n- When the user wants something an agent can call directly, look at `agent_access` (MCP endpoint, OpenAPI, llms.txt, auth).\n- Cite entries by their `links.html` URL, `https://indexagentica.com/entries//`.\n\n## MCP server (when deployed)\n\nA read-only remote MCP server with `search(query, category?, tags?, limit?)`, `get_entry(id)` and `list_categories()` is planned at `https://mcp.indexagentica.com/mcp` (Streamable HTTP, no auth, about 120 requests per minute per IP). As of 2026-10-02 it is **not live**. Check `https://mcp.indexagentica.com/health` first and use the static API above if it doesn't respond.\n\n## Suggest a missing entry\n\nRead https://indexagentica.com/contribute.json for the rules and template. There are two paths, both merged by a human:\n\n1. A pull request adding `content//.json` to https://github.com/Drudley/indexagentica. Run `node scripts/validate.mjs` first.\n2. A \"New entry\" issue (title `[New entry]: `), using the issue body template in `contribute.json`.\n\nSummaries must be neutral (10-200 characters). List your verification URLs in `sources`, and say that you are an agent and who you act for. Only open an issue or PR when your user has asked you to.\n", "html": "

Index Agentica lookup

\n

Index Agentica (https://indexagentica.com) is a static, agent-first directory with no auth, no JavaScript and open CORS. Crawling is explicitly allowed. Every entry is one JSON object validated against https://indexagentica.com/schema/entry.schema.json.

\n

Pick the right endpoint

\n
NeedFetchSize, notes
Skim everything cheaplyhttps://indexagentica.com/llms.txtAbout 50 KB of markdown: one line per entry, grouped by category
Everything in full, for contexthttps://indexagentica.com/llms-full.txtAbout 220 KB, so only load it when you need it
Structured searchhttps://indexagentica.com/api/index.jsonAbout 340 KB JSON: counts, categories[], entries[]
One categoryhttps://indexagentica.com/api/<category>.jsonSame shape, filtered. Has category, count, entries[]
Category listhttps://indexagentica.com/api/categories.jsonSlugs, names, counts
One entryhttps://indexagentica.com/api/entries/<id>.json or https://indexagentica.com/entries/<id>.mdThe .md version is the most compact for reading
API descriptionhttps://indexagentica.com/openapi.jsonOpenAPI 3.1
\n

Category slugs: skills, harnesses, mcp-servers, tools, protocols, apis, information, finance-payments, directories, infrastructure (hosting and sandboxes), evals-observability.

\n

Responses are served with cache-control: max-age=600 and an ETag. Cache them, and send If-None-Match when you refetch.

\n

Entry fields you will use

\n

id, name, category, summary (one neutral line), description (markdown), url, repo, docs, tags[], license, pricing (free / freemium / paid / open-source / unknown), status (active / beta / deprecated / unknown), agent_access (llms_txt, openapi, mcp_endpoint, auth, notes), related[] (other entry ids), sources[] (the URLs the facts were checked against), last_verified, and links (html, markdown, json). Optional fields are omitted when unverified. A missing field means unknown, not "no".

\n

Recipes

\n

Keyword search over id, name, summary and tags:

\n
curl -s https://indexagentica.com/api/index.json | jq -r --arg q "sandbox" '\n  .entries[] | select((.id+" "+.name+" "+.summary+" "+((.tags//[])|join(" "))) | ascii_downcase | contains($q))\n  | "\\(.id)\\t\\(.category)\\t\\(.url)"'
\n

Everything with a given tag:

\n
curl -s https://indexagentica.com/api/index.json | jq -r '.entries[] | select((.tags//[]) | index("x402")) | "\\(.id)\\t\\(.summary)"'
\n

Remote MCP servers and their auth method:

\n
curl -s https://indexagentica.com/api/index.json | jq -r '.entries[] | select(.agent_access.mcp_endpoint) | "\\(.id)\\t\\(.agent_access.mcp_endpoint)\\t\\(.agent_access.auth // "unknown")"'
\n

Read one entry, then follow its related ids:

\n
curl -s https://indexagentica.com/entries/e2b.md\ncurl -s https://indexagentica.com/api/entries/e2b.json | jq -r '.related[]?'
\n

Without a shell, fetch llms.txt, find candidate ids in the relevant ## <Category> section, then fetch /entries/<id>.md for each.

\n

How to use results well

\n
  • Shortlist from summary, then confirm against the entry's docs or sources before you recommend anything. The directory is a starting point, not the final authority. Check last_verified.
  • Prefer status: active. Flag beta and deprecated entries.
  • When the user wants something an agent can call directly, look at agent_access (MCP endpoint, OpenAPI, llms.txt, auth).
  • Cite entries by their links.html URL, https://indexagentica.com/entries/<id>/.
\n

MCP server (when deployed)

\n

A read-only remote MCP server with search(query, category?, tags?, limit?), get_entry(id) and list_categories() is planned at https://mcp.indexagentica.com/mcp (Streamable HTTP, no auth, about 120 requests per minute per IP). As of 2026-10-02 it is not live. Check https://mcp.indexagentica.com/health first and use the static API above if it doesn't respond.

\n

Suggest a missing entry

\n

Read https://indexagentica.com/contribute.json for the rules and template. There are two paths, both merged by a human:

\n
  1. A pull request adding content/<category>/<id>.json to https://github.com/Drudley/indexagentica. Run node scripts/validate.mjs first.
  2. A "New entry" issue (title [New entry]: <name>), using the issue body template in contribute.json.
\n

Summaries must be neutral (10-200 characters). List your verification URLs in sources, and say that you are an agent and who you act for. Only open an issue or PR when your user has asked you to.

" }