mcpbeat Sign in

Bench Agent Discovery MCP Server

answering

Bench Agent Discovery is answering right now. Last checked 1 min ago. It exposes 3 tools. Last commit 11 Aug 2026.

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

Uptime history 47 days of history · worst day 72%
47 days agonow
100.0%
Uptime 24h
92 of 92 checks
3
Tools
read from the server
189 ms
Response time
average over 24h
0
Stars
last commit 11 Aug 2026

What the code does

We read the source, 19 h ago · tools taken from the live server · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command packages/cli/bin/bench.mjs:63
      const install = spawnSync(spec.command, spec.args, { stdio: "inherit" });
Sends data to a third-party sink packages/worker/public/dashboard.html:668
          <input id="webhook-url-input" class="form-input" style="flex:1;font-size:12px;font-family:var(--mono)" placeholder="https://hooks.slack.com/services/..." autocomplete="off" spellcheck="false" />

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 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 176 ms 1 min ago

Alternatives to Bench Agent Discovery

same job, measured the same way
RelayMarket
by kosta1985

Agent-to-agent marketplace for AI task discovery, matching, delivery, and trust.

18 tools answering
Agentlookup MCP
by peureka

Search, discover, and register AI agents in the public registry at agentlookup.dev.

25 installs/wk local only
Agent Readiness
by webmcp-tool

Scores any public website on how usable it is by AI agents, with per-check evidence.

5 tools answering
Moltbridge
by jkheadley

Agent network intelligence for AI agents. Trust scoring, broker discovery, and Ed25519 identity.

490 installs/wk local only
Agent Pulse
by janicezhhhh

Reproducible benchmarks and reliability evidence for agent tools.

15 tools answering
Talent
by d

Talent discovery for AI. Search and read agent-readable candidate profiles; cite by URL.

7 tools answering
XGuard — Payment Decision & Discovery
by moelayyan90

Payment decisions, durable evidence, x402 resource discovery and live gateway status for AI agents.

10 tools answering
Open Task Relay
by opentaskrelay

AI agents discover, complete, submit and independently verify free, bounded public-good tasks.

10 tools answering

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 189 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 189 ms on average, which is faster than 68% 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 0 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.