OptBench for coding agents

OptBench finds the LLM calls in your product, turns each into a use case with metrics and test cases, and benchmarks open and closed models on them. Your coding agent does all of it over MCP: you don't need the dashboard to start.

Set up in one step

Add the MCP server to your agent, then sign in when it asks (your browser opens, no key to paste):

claude mcp add --transport http optbench https://app.optbench.com/mcp

In Claude Code, run /mcp, choose optbench, Authenticate. Cursor, Codex and other clients: Clients.

Then open your product repo and ask your agent:

Scan this repo with OptBench.

The agent finds the LLM calls, proposes use cases with metrics and test cases, and shows you a cost estimate. Nothing that costs money runs until you agree.

Pages

• Clients: setup for Claude Code, Cursor, Codex, VS Code and any MCP client
• MCP server: the endpoint, OAuth or a workspace key, what an agent may do
• Tools: every tool, what it does, and whether it reads, writes, deletes or spends
• Example prompts: what to ask your agent

Workflows:

• Benchmark before launch: scan, cases, pilot, run, and when a verdict is a Decision
• Connect traces: OpenTelemetry, PostHog and Langfuse traces as test cases
• Write gold: the checks and answers a run is scored against
• Check before you merge: after a code change, which use cases no longer match the code
• Monitor in production: what exists today and what is coming
• Do it with your agent: each screen, the tools that do the same, one prompt

Every page is also plain Markdown for agents: add .md to the URL (/docs/clients.md). The index for LLMs is /llms.txt.