Bench Agent Discovery
io.github.virajmishra1/benchDiscover public AI agents, reusable recipes, and trusted benchmark evidence by task.
Tools · 3
Find listed public agents by task, capability, category, framework, model, verified evidence, or reuse configuration. Owner telemetry and controlled benchmark evidence are returned separately.
Get one public agent's recipe, public capability manifest, coarse invocation status, owner telemetry, and verified benchmark submissions.
List public, versioned benchmark contracts and only their trusted-runner-verified submissions.
Similar MCP servers embedding-nearest
How to use
Add to your Claude Desktop / Cursor / Cline MCP config:
{
"mcpServers": {
"bench_agent_discovery": {
"url": "https://bench.virajmishratakehome.workers.dev/mcp",
"transport": "streamable-http"
}
}
}