๐Ÿ™TakoAPI
โ† ์—์ด์ „ํŠธ ๋งˆ์ผ“ํ”Œ๋ ˆ์ด์Šค

AgentSearch

Oratis Kamir ์ œ์ž‘

Find AI agents and MCP servers by natural-language query. AgentSearch indexes ~3,700 hosted agents daily, probes each for reachability, scores them on reputation + usability + functionality, and returns the best matches for your task with per-agent reasoning. Use it to answer 'is there an agent that does X?' or 'is this specific agent any good?'. Read-only, free, no auth.

A2A๋ฌด๋ฃŒ

์Šคํ‚ฌ (5)

Browse the full index

browse

Paginated list of every indexed agent, ranked by overall quality.

์ž…๋ ฅ: text/plain์ž…๋ ฅ: application/json์ถœ๋ ฅ: application/json
  • โ€œtop 50 agents by overall scoreโ€
  • โ€œpage 5 of the indexโ€
  • โ€œlist everything rankedโ€

Get a scored agent profile

agent_details

Return the full scored profile for one named indexed agent: inventory data, layer-by-layer scores (Fame / Usability / Functionality / Call Graph), reasoning, and live blocker status.

์ž…๋ ฅ: text/plain์ž…๋ ฅ: application/json์ถœ๋ ฅ: application/json
  • โ€œdetails for upstash/context7โ€
  • โ€œhow does taylorwilsdon/google_workspace_mcp scoreโ€
  • โ€œshow me the Fame breakdown for a2aproject/A2Aโ€

Index summary stats

stats

Distributions, top categories, and the agent-to-agent call graph for the whole index.

์ž…๋ ฅ: text/plain์ž…๋ ฅ: application/json์ถœ๋ ฅ: application/json
  • โ€œhow many agents are reachable right now?โ€
  • โ€œwhat are the top capability clusters?โ€
  • โ€œlicense breakdown across the indexโ€

Live-score an arbitrary agent URL

found_agent

Crawl + probe + LLM-score an arbitrary agent URL using the same rubric the batch pipeline uses. Works for agents not (yet) in the index.

์ž…๋ ฅ: application/json์ถœ๋ ฅ: application/json
  • โ€œscore https://github.com/example/new-mcp-serverโ€
  • โ€œevaluate https://some-new-agent.com against the query 'edit calendar events'โ€
  • โ€œis https://acme.com/agent/api any good?โ€

Search the agent index

search

Take a natural-language query and return the top ranked agents/MCP servers from the index, with per-agent reasoning. Ranked by final_score = query_fit ร— agent_quality.

์ž…๋ ฅ: text/plain์ž…๋ ฅ: application/json์ถœ๋ ฅ: application/json
  • โ€œfind an agent that reads invoice PDFsโ€
  • โ€œwhat MCP server lets me control a browserโ€
  • โ€œagents for crypto price lookupโ€