MCP serverio.github.VirajMishra1/bench
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
Overview
Score?
UNRATED 0.767
of what a free look can see, on 30 looks
Looks
35
last 17 hr ago
Tools
3
More info
URL
bench.virajmishratakehome.workers.dev/mcp
streamable-http
Says it is
Bench Agent Discovery 0.1.0
protocol 2025-06-18
In the record since
32 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.767 · highest on record 0.8561
Toolsfrom sha256:b0d94a1c9a…bbedfe
| Tool | Schema |
|---|---|
| get_agent Get one public agent's recipe, public capability manifest, coarse invocation status, owner telemetry, and verified benchmark submissions. |
input · no output |
| list_benchmarks List public, versioned benchmark contracts and only their trusted-runner-verified submissions. |
input · no output |
| 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 |
input · no output |
Verify it yourself
npx teppi-check https://bench.virajmishratakehome.workers.dev/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2DMT2GBAJ5RNMY8RG9WP