3 tagged agent-testing, measured the same way as everything else here.
MCP server Claude CodeCodexCursor +2
Reticle CLI, bridge and MCP server: a coding agent drives your running web app from the inside and gets a verdict with evidence, for change verification, access control, accessibility, performance and SEO checks. Runs locally from the @reticlehq/server npm package.
MCP server Claude CodeCodexCursor +2
The graph your agent actually follows — induce a behavioral spec from agent traces, then check, diff, and gate against it. Runs locally from the tracegraph npm package.
MCP server Claude CodeCodexCursor +2
Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform. Runs locally from the @verifyax/mcp-server npm package. Needs 2 environment variables to run.