mcpbeat

Bench Agent Discovery MCP Server

io.github.VirajMishra1/bench
answering

Bench Agent Discovery is answering right now. Last checked 2 min ago. It exposes 3 tools. Last commit 24 Jul 2026.

Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.

Uptime history 41 hours of history
41 hours agonow
100.0%
Uptime 24h
92 of 92 checks
3
Tools
read from the server
160 ms
Response time
average over 24h
1
Stars
last commit 24 Jul 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

run in your terminal
claude mcp add bench --transport http https://bench.virajmishratakehome.workers.dev/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "bench": {
      "url": "https://bench.virajmishratakehome.workers.dev/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.bench]
url = "https://bench.virajmishratakehome.workers.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "bench": {
      "url": "https://bench.virajmishratakehome.workers.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "bench": {
      "url": "https://bench.virajmishratakehome.workers.dev/mcp"
    }
  }
}

Available tools 3

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent
get_agent
Get one public agent's recipe, public capability manifest, coarse invocation status, owner telemetry, and verified benchmark submissions.
agents
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.
benchmarks
list_benchmarks
List public, versioned benchmark contracts and only their trusted-runner-verified submissions.

Endpoints

URLTransportStateLatencyChecked
https://bench.virajmishratakehome.workers.dev/mcp streamable-http answering 312 ms 2 min ago

Bench Agent Discovery — questions

Answers built from our own checks of this server.

What can Bench Agent Discovery do?
It exposes 3 tools, read directly from the server on our last check. Among them: get_agent, list_benchmarks, search_agents. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Bench Agent Discovery working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 160 ms. The bar chart above shows every period we have measured.
How do I connect Bench Agent Discovery?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Bench Agent Discovery need an API key?
No. Bench Agent Discovery completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 3 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Bench Agent Discovery?
It answers our handshake in 160 ms on average, which is faster than 71% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Bench Agent Discovery open source?
Yes — it is published under the MIT licence, written in TypeScript and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.