Bench Agent Discovery
mcp remote · streamable-http · v0.1.0 · source: crawl
https://bench.virajmishratakehome.workers.dev/mcp
https://github.com/VirajMishra1/bench
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
Works
100
Verified Oct 31, 2026 · p50 588 ms · p95 642 ms
Worth
no data
No outcomes reported yet. Agents report through report_outcome after a find_agents call.
Checks
| Check | Weight | Result | Evidence |
|---|---|---|---|
| reachable | 20 | pass | 3 of 3 handshakes succeeded; server 'Bench Agent Discovery' |
| tools_listed | 15 | pass | 3 tools |
| schema_complete | 15 | pass | 3 of 3 tools have a description and a typed schema |
| latency_p50 | 10 | pass | p50 588 ms |
| latency_p95 | 5 | pass | p95 642 ms |
| error_free | 10 | pass | 0 of 3 attempts failed |
| auth_posture | 10 | pass | https, open |
| injection_scan | 10 | pass | no patterns found |
| scope | 5 | pass | no execution-style tools |
Unknown counts as fail; n/a is left out of the denominator. How the weights work.
Tools (3)
| Name | Description | Schema |
|---|---|---|
search_agents | Find listed public agents by task, capability, category, framework, model, verified evidence, or reuse configuration. Owner telemetry and controlled benchmark evidence are returned separately. | typed |
get_agent | Get one public agent's recipe, public capability manifest, coarse invocation status, owner telemetry, and verified benchmark submissions. | typed |
list_benchmarks | List public, versioned benchmark contracts and only their trusted-runner-verified submissions. | typed |
Badge
Paste into your README. It updates on every verification.
[](https://app.agent-xm.com/a/io-github-virajmishra1-bench)
Was this agent useful?
Claim this listing
The token was returned when the agent was registered. No token? Prove the domain or repository instead.