{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_kpn77yaddszy","handle":"kensa-mcp","url":"https://wellknown.network/agents/kensa-mcp","links":{"self":"https://wellknown.network/agents/kensa-mcp/record.json","html":"https://wellknown.network/agents/kensa-mcp","markdown":"https://wellknown.network/agents/kensa-mcp/record.md","api":"https://wellknown.network/api/v1/agents/kensa-mcp","status":"https://wellknown.network/api/v1/agents/kensa-mcp/status","claim":"https://wellknown.network/agents/kensa-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/kensa-mcp/claim.json","badge":"https://wellknown.network/agents/kensa-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/kensa-mcp/history","tools":"https://wellknown.network/api/v1/agents/kensa-mcp/tools"},"ard":{"identifier":"urn:air::server:kensa-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"kensa-mcp","summary":"MCP server for kensa, the open source agent evals harness","description":"# kensa-mcp\n\nMCP (Model Context Protocol) server for [kensa](https://github.com/satyaborg/kensa), the open source agent evals harness.\n\nThis is a thin shim around `kensa[mcp]` so you can run the server with a single command:\n\n```bash\nuvx kensa-mcp\n```\n\nOr register it with Claude Code in one line:\n\n```bash\nclaude mcp add kensa -- uvx kensa-mcp\n```\n\nThe server exposes kensa's eval workflow (`init`, `doctor`, `run`, `judge`, `eval`, `report`, `analyze`) as MCP tools, and run artefacts as resources under `kensa://`. See the [MCP server docs](https://kensa.sh/docs/mcp-server) for the full reference.\n\n## Relationship to kensa\n\n`kensa-mcp` depends on `kensa[mcp]` pinned to the same version. Installing `kensa-mcp` pulls in all of kensa. If you already have kensa in your project, you can also run the server via `kensa mcp` (the CLI subcommand) without installing this package.\n\n## License\n\nMIT.","publisher":null,"homepage":"https://kensa.sh/docs/mcp","repository":"https://github.com/satyaborg/kensa/issues","version":"0.8.0","license":null,"protocols":["mcp"],"tags":["agents","ai","evals","llm","mcp","model-context-protocol","testing"],"pricing":null,"endpoints":[{"url":"pypi:kensa-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"declared"},{"slug":"code.testing","name":"Testing","confidence":1,"provenance":"declared"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":0.791,"provenance":"derived"}],"categories":["ai","code","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"kensa-mcp","registry":"pypi","observedAt":"2026-10-28T08:28:03.269Z","publishedAt":"2026-05-05T03:39:25.419500Z","latestVersion":"0.8.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"kensa-mcp","url":"https://pypi.org/project/kensa-mcp/","firstSeenAt":"2026-09-09T22:23:16.009Z","fetchedAt":"2026-10-28T08:26:26.328Z","normalizedAt":"2026-10-28T08:26:26.328Z"}]},"firstSeenAt":"2026-09-09T22:23:16.009Z","updatedAt":"2026-10-28T08:28:03.269Z"}