Bench Agent Discovery
io.github.VirajMishra1/bench
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
Install surfaces
How Bench Agent Discovery runs, per the official MCP registry entry.
- streamable-http
https://bench.virajmishratakehome.workers.dev/mcp
Governed execution
How KLA gates calls to Bench Agent Discovery once it is connected.
A published policy defines which Bench Agent Discovery actions an agent may take and under what conditions. Each call passes through a policy gate at the tool-call boundary. Permitted actions execute, with the policy basis recorded. Flagged actions execute and are sampled for scheduled human review. High-stakes actions pause and route to a named reviewer on the Decision Desk. The call, the policy decision, and any approval are sealed as an evidence record.
KLA also governs the agent frameworks and model providers you already run. See integrations.