{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_v89ayeukpxcz","handle":"agent-eval","url":"https://wellknown.network/agents/agent-eval","links":{"self":"https://wellknown.network/agents/agent-eval/record.json","html":"https://wellknown.network/agents/agent-eval","markdown":"https://wellknown.network/agents/agent-eval/record.md","api":"https://wellknown.network/api/v1/agents/agent-eval","status":"https://wellknown.network/api/v1/agents/agent-eval/status","claim":"https://wellknown.network/agents/agent-eval/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agent-eval/claim.json","badge":"https://wellknown.network/agents/agent-eval/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:agent-eval","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"agent-eval","summary":"Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.","description":"Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.","publisher":{"name":"RudrenduPaul","url":null},"homepage":"https://github.com/RudrenduPaul/agent-eval","repository":"https://github.com/RudrenduPaul/agent-eval","version":"0.1.8","license":"Apache-2.0","protocols":["mcp"],"tags":["agents","benchmark","ci-cd","cohen-d","crewai","eval","langgraph","llm","mann-whitney","openai-agents","p-value","promptfoo-alternative","regression","statistics","testing"],"pricing":null,"endpoints":[{"url":"pypi:agent-regress-cli","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-08-10T20:36:26.103189Z","publishedAt":"2026-08-10T20:36:26.103189Z","registryName":"io.github.RudrenduPaul/agent-eval"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","license":"pypi","repoUrl":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"pypi","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"code.testing","name":"Testing","confidence":1,"provenance":"declared"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":1,"provenance":"declared"},{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"declared"}],"categories":["ai","code","dev"]},"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":"agent-regress-cli","registry":"pypi","observedAt":"2026-09-06T06:19:20.335Z","publishedAt":"2026-08-11T14:27:10.223019Z","latestVersion":"0.1.9"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"io.github.RudrenduPaul/agent-eval","url":"https://registry.modelcontextprotocol.io/v0/servers/io.github.RudrenduPaul%2Fagent-eval","firstSeenAt":"2026-09-06T06:18:07.568Z","fetchedAt":"2026-09-06T06:18:07.568Z","normalizedAt":"2026-09-06T06:18:07.568Z"},{"source":"pypi","key":"agent-regress-cli","url":"https://pypi.org/project/agent-regress-cli/","firstSeenAt":"2026-09-06T06:18:46.599Z","fetchedAt":"2026-09-06T06:18:46.599Z","normalizedAt":"2026-09-06T06:18:46.599Z"}]},"firstSeenAt":"2026-09-06T06:18:07.568Z","updatedAt":"2026-09-06T06:19:20.335Z"}