Index Agentica lookup
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.
Download
- indexagentica-lookup.zip (the whole skill folder)
- SKILL.md (raw)
Install by unzipping into your agent's skills directory, e.g. for Claude Code: curl -sLO https://indexagentica.com/skills/indexagentica-lookup.zip && unzip -o indexagentica-lookup.zip -d ~/.claude/skills/
Files
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.
SKILL.md
Index Agentica lookup
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.
Pick the right endpoint
| Need | Fetch | Size, notes |
|---|---|---|
| Skim everything cheaply | https://indexagentica.com/llms.txt | About 50 KB of markdown: one line per entry, grouped by category |
| Everything in full, for context | https://indexagentica.com/llms-full.txt | About 220 KB, so only load it when you need it |
| Structured search | https://indexagentica.com/api/index.json | About 340 KB JSON: counts, categories[], entries[] |
| One category | https://indexagentica.com/api/<category>.json | Same shape, filtered. Has category, count, entries[] |
| Category list | https://indexagentica.com/api/categories.json | Slugs, names, counts |
| One entry | https://indexagentica.com/api/entries/<id>.json or https://indexagentica.com/entries/<id>.md | The .md version is the most compact for reading |
| API description | https://indexagentica.com/openapi.json | OpenAPI 3.1 |
Category slugs: skills, harnesses, mcp-servers, tools, protocols, apis, information, finance-payments, directories, infrastructure (hosting and sandboxes), evals-observability.
Responses are served with cache-control: max-age=600 and an ETag. Cache them, and send If-None-Match when you refetch.
Entry fields you will use
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".
Recipes
Keyword search over id, name, summary and tags:
curl -s https://indexagentica.com/api/index.json | jq -r --arg q "sandbox" '
.entries[] | select((.id+" "+.name+" "+.summary+" "+((.tags//[])|join(" "))) | ascii_downcase | contains($q))
| "\(.id)\t\(.category)\t\(.url)"'Everything with a given tag:
curl -s https://indexagentica.com/api/index.json | jq -r '.entries[] | select((.tags//[]) | index("x402")) | "\(.id)\t\(.summary)"'Remote MCP servers and their auth method:
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")"'Read one entry, then follow its related ids:
curl -s https://indexagentica.com/entries/e2b.md
curl -s https://indexagentica.com/api/entries/e2b.json | jq -r '.related[]?'Without a shell, fetch llms.txt, find candidate ids in the relevant ## <Category> section, then fetch /entries/<id>.md for each.
How to use results well
- Shortlist from
summary, then confirm against the entry'sdocsorsourcesbefore you recommend anything. The directory is a starting point, not the final authority. Checklast_verified. - Prefer
status: active. Flagbetaanddeprecatedentries. - 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.htmlURL,https://indexagentica.com/entries/<id>/.
MCP server (when deployed)
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.
Suggest a missing entry
Read https://indexagentica.com/contribute.json for the rules and template. There are two paths, both merged by a human:
- A pull request adding
content/<category>/<id>.jsonto https://github.com/Drudley/indexagentica. Runnode scripts/validate.mjsfirst. - A "New entry" issue (title
[New entry]: <name>), using the issue body template incontribute.json.
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.
Directory entries in this skill
- llms.txt: Proposal to standardize a /llms.txt Markdown file that gives LLMs and agents a concise guide to a website's content.
- Model Context Protocol (MCP): Open protocol that standardizes how AI applications connect to external tools, data sources and prompts via MCP servers.
- OpenAPI Specification: Language-agnostic standard for describing HTTP APIs, widely used to generate agent tools from API definitions.
Related
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