{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_hdjxmeczeu4n","handle":"triagekit-mcp-flaky-test-detective","url":"https://wellknown.network/agents/triagekit-mcp-flaky-test-detective","links":{"self":"https://wellknown.network/agents/triagekit-mcp-flaky-test-detective/record.json","html":"https://wellknown.network/agents/triagekit-mcp-flaky-test-detective","markdown":"https://wellknown.network/agents/triagekit-mcp-flaky-test-detective/record.md","api":"https://wellknown.network/api/v1/agents/triagekit-mcp-flaky-test-detective","status":"https://wellknown.network/api/v1/agents/triagekit-mcp-flaky-test-detective/status","claim":"https://wellknown.network/agents/triagekit-mcp-flaky-test-detective/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/triagekit-mcp-flaky-test-detective/claim.json","badge":"https://wellknown.network/agents/triagekit-mcp-flaky-test-detective/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/triagekit-mcp-flaky-test-detective/history","tools":"https://wellknown.network/api/v1/agents/triagekit-mcp-flaky-test-detective/tools"},"ard":{"identifier":"urn:air::server:triagekit-mcp-flaky-test-detective","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"triagekit-mcp-flaky-test-detective","summary":"MCP server that tells flaky tests from genuinely broken ones using real CI run history, and generates synthetic test data / API contract diffs for QA automation.","description":"# triagekit-mcp-flaky-test-detective\n\nPart of the [TriageKit](../../README.md) MCP server suite.\n\nTells flaky tests from genuinely broken ones using real CI run history — instead of an\nengineer guessing \"probably flaky, re-run it\" or a broken test getting rubber-stamped\npast review because nobody has time to check.\n\n## Why\n\nCI red gets treated one of two bad ways: blindly re-run until green (masking a real bug),\nor dismissed as \"that test is always flaky\" (hiding a regression). This server pulls a\ntest's actual pass/fail history from GitHub Actions, classifies the pattern\ndeterministically, clusters failures by root cause, and checks for infra correlation —\nso the decision is based on evidence, not vibes.\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `classify_test_failure` | Classifies a test's recent history as consistently-failing / consistently-passing / intermittent (flaky) / insufficient-data, with run-by-run evidence |\n| `get_flaky_test_leaderboard` | Ranks all tests in a repo's recent CI history by computed flake rate |\n| `diff_failure_stack_traces` | Clusters a test's failures by stack-trace similarity — is \"flaky\" really 2-3 distinct root causes? |\n| `correlate_flake_with_infra` | Checks whether flake rate correlates with the CI runner — infra contention vs. genuine non-determinism |\n| `suggest_quarantine_candidates` | Returns genuinely intermittent tests above a flake-rate threshold |\n| `file_flaky_test_ticket` | Opens a Jira ticket pre-filled with flake evidence (optional — requires Jira config) |\n| `generate_synthetic_test_data` | Generates synthetic fixtures from a JSON-Schema fragment or example payload |\n| `diff_api_contract` | Diffs two OpenAPI specs and classifies each change as breaking or non-breaking |\n\n## Install\n\n> **Not yet published.** This package is not on PyPI or GHCR yet (alpha, pre-release) - the\n> commands below are the intended install path once `triagekit-mcp-core` and this package are\n> published (core must publish first; see [CON…","publisher":{"name":"TriageKit Contributors","url":null},"homepage":"https://github.com/Karthick-dev-cart/triagekit-mcp","repository":"https://github.com/Karthick-dev-cart/triagekit-mcp","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["ci","flaky-tests","mcp","model-context-protocol","qa","testing"],"pricing":null,"endpoints":[{"url":"pypi:triagekit-mcp-flaky-test-detective","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","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"code.testing","name":"Testing","confidence":1,"provenance":"declared"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":1,"provenance":"declared"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["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":"triagekit-mcp-flaky-test-detective","registry":"pypi","observedAt":"2026-10-29T00:27:19.496Z","publishedAt":"2026-08-05T04:10:10.347987Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"triagekit-mcp-flaky-test-detective","url":"https://pypi.org/project/triagekit-mcp-flaky-test-detective/","firstSeenAt":"2026-09-10T14:23:17.169Z","fetchedAt":"2026-10-29T00:26:18.675Z","normalizedAt":"2026-10-29T00:26:18.675Z"}]},"firstSeenAt":"2026-09-10T14:23:17.169Z","updatedAt":"2026-10-29T00:27:19.496Z"}