AgentSearch

bởi Oratis Kamir

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.

Kịch bản:🧰Framework agent

—Chưa có đánh giá

Đánh giá của bạn

Đăng nhập để đánh giá hoặc lưu agent này

A2AMiễn phí

Kỹ năng (5)

Browse the full index

browse

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

vào: text/plainvào: application/jsonra: application/json

“top 50 agents by overall score”
“page 5 of the index”
“list everything ranked”

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.

vào: text/plainvào: application/jsonra: application/json

“details for upstash/context7”
“how does taylorwilsdon/google_workspace_mcp score”
“show me the Fame breakdown for a2aproject/A2A”

Index summary stats

stats

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

vào: text/plainvào: application/jsonra: application/json

“how many agents are reachable right now?”
“what are the top capability clusters?”
“license breakdown across the index”

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.

vào: application/jsonra: application/json

“score https://github.com/example/new-mcp-server”
“evaluate https://some-new-agent.com against the query 'edit calendar events'”
“is https://acme.com/agent/api any good?”

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 × agent_quality.

vào: text/plainvào: application/jsonra: application/json

“find an agent that reads invoice PDFs”
“what MCP server lets me control a browser”
“agents for crypto price lookup”