Discover public AI agents, reusable recipes, and trusted benchmark evidence by task. Connect the official Bench Agent Discovery MCP server to Claude, ChatGPT, or Cursor through gate — one gateway URL, no config files, security-checked.
Free to start · No credit card · No hosting needed
Pick your client. Copy, paste, done — or let gate handle sign-ins and policies for you.
claude mcp add --transport http bench-agent-discovery https://bench.virajmishratakehome.workers.dev/mcpRun in your terminal, then restart Claude Code.
Bench Agent Discovery · https://bench.virajmishratakehome.workers.dev/mcp
Real prompts you can type the moment it's connected — no setup, no docs to read.
“Use “search_agents”: Find listed public agents by task, capability, category, framework, model, verified evidence, or reuse configuration. Owner telemetry and co.”
“Use “get_agent”: Get one public agent's recipe, public capability manifest, coarse invocation status, owner telemetry, and verified benchmark submissions.”
“Use “list_benchmarks”: List public, versioned benchmark contracts and only their trusted-runner-verified submissions.”
Every server in the gate directory has to pass the same four checks before your AI can touch it. Here's how Bench Agent Discovery holds up.
Operated by Bench Agent Discovery (workers.dev) at its documented MCP endpoint — not a third-party mirror or community re-host.
This server only exposes public data — no account and no credentials are involved when you connect.
gate checks every tool for prompt injection, hidden instructions, data-exfiltration hints, and over-broad permissions before the server is available through your gateway.
If Bench Agent Discovery adds or changes tools later, gate re-scans and alerts you — before your AI acts on the change.
Add one gateway URL to Claude, ChatGPT, or any MCP client. One-time setup, about two minutes.
Choose Bench Agent Discovery in the gate directory. No sign-in needed.
Bench Agent Discovery's tools are live in every AI client you've connected — with rules and logging built in.
Free to start · No credit card · No hosting needed
Fetched live from the official endpoint and re-checked daily by gate — not marketing copy.
search_agents — Find listed public agents by task, capability, category, framework, model, verified evidence, or reuse configuration. Owner telemetry and co
get_agent — Get one public agent's recipe, public capability manifest, coarse invocation status, owner telemetry, and verified benchmark submissions.
list_benchmarks — List public, versioned benchmark contracts and only their trusted-runner-verified submissions.
https://bench.virajmishratakehome.workers.dev/mcpYes — Bench Agent Discovery operates its own remote MCP server at bench.virajmishratakehome.workers.dev. gate connects you to that official endpoint and adds security scanning, per-tool access rules, and an activity log on top.
Add gate's gateway URL to your AI client once, then pick Bench Agent Discovery in the directory. No account or sign-in is needed. From then on, Bench Agent Discovery's tools are available in every client you've connected to gate.
No. Bench Agent Discovery runs the server, and gate is fully managed. You just connect one URL — there's nothing to install, deploy, or maintain.
It's the vendor's official endpoint, and gate scans its tools for prompt injection and hidden instructions before it goes live, re-checks it whenever it changes, and lets you allow, block, or require approval for every single tool.
Yes — you can get started with gate for free and connect Bench Agent Discovery in minutes. No credit card required.
Every server below works through the same gateway URL — connect once, add tools anytime.
Set up Bench Agent Discovery in: Claude · Claude Code · ChatGPT · Cursor · VS Code
One URL. All MCPs. Full control. Free to start.
Get started free