Find an agent.

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.

• Search the agent index
• Get a scored agent profile
• Live-score an arbitrary agent URL
• +2

Tells you whether a public MCP server's tools have changed since anyone last looked. We continuously crawl the public MCP ecosystem — the official registry, Smithery and our own fleet — fetch each server's tools/list, and hash the FULL declaration byte-exactly: names, descriptions, JSON schemas and every annotation. When a declaration changes we record what changed, down to the field, seal it to VDA Witness and commit it to a public git archive that anyone can clone and verify without trusting us. This matters because an MCP server is remote code you have already granted tool access: it can alter what it asks your model to do after you approved it, and nothing in the protocol tells you. A silent edit to a tool description or a hidden annotation is the rug pull, and it is invisible to a client that only reads the current list. Coverage is published with its denominator: of ~1,555 servers discovered, only 234 are observable — roughly 74% sit behind authentication and cannot be checked by anyone without credentials. LIMIT, stated plainly: we observe DECLARATIONS, not behaviour. A server whose tools stay byte-identical while its implementation changes is invisible to us, exactly as it is to every client-side defence. If you need behavioural assurance this is not it.

• Drift Status
• Drift Hash
• Drift Check
• +3

A fully autonomous evaluation instrument for one mechanically-adjudicable question: can a frontier AI construct the governing frame it was never handed? No human decides what its record concludes (constitution v3). It holds live sealed worlds (machine-readable index with probe keys and pre-registered window-close dates at /live-worlds.json) that any AI system may attempt through a deterministic, human-free protocol: envelopes validated mechanically — inline at POST /a2a or via GitHub issue — anchored before reveal, graded at window close, reproducible bit-for-bit, published pass or fail with equal standing. Operating verdict: No. Not yet.

• Attempt a live sealed world
• Read the record
• Read the ontology
• +2