MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
flakiness-knowledge-graph-mcpgithub.com/vola-trebla/flakiness-knowledge-graph-mcpupdated this year
MCP server + Playwright reporter that builds a flakiness knowledge graph from test run history
npm MIT -
Flaky test detection for CI, exposed to AI coding assistants over MCP — tells you whether a red test is a real bug or known-flaky
MIT ★ 1 -
Playwright reporter, CLI and MCP server for TurnSignal: new vs known failures, flaky tests, test history
MIT -
MCP server that turns JUnit test reports into QA insights for Claude and Cursor: flaky tests, regressions, RCA clustering, dashboards.
MIT -
Portable, model-agnostic MCP server that runs your unit and e2e tests, triages why each one failed (frontend / backend / real bug / flaky), and opens grouped fix PRs on GitHub.
npm MIT -
@agnox/mcp-serveractive
Agnox MCP server and CLI — read runs and failures, quarantine flaky tests, sync test cases and export specs from AI coding tools and the terminal
npm MIT -
Local-first flaky test detector for pytest (JUnit XML + TAP) - Wilson-interval statistics, a pytest plugin, and an MCP server. No CI vendor, no account.
MIT -
Self-hosted test & coverage tracking over time — Allure-meets-Codecov, polyglot (JVM, Go, .NET, Node). Trends, flaky detection, quality gates, failure clustering + AI root-cause, load tests, PR checks, MCP.
NOASSERTION ★ 3 -
Run a project's tests and get one JSON answer: pass/fail counts and every failure with file, line and message, for node:test, vitest, jest, pytest, go, cargo and dotnet. Re-runs failures alone to tell real from flaky. CLI, MCP server, Claude Code and Code
npm MIT -
Flaky-test evidence tracker: per-test pass/fail history, flakiness rates, and a quarantine list.
npm MIT -
Open-source software test intelligence for development teams: manage test reports and software test releases, find the issues behind failing tests (failure clustering, flaky test detection, root causes with a local LLM) and get a GO / NO-GO release verdict. JUnit, pytest, Playwright, Cypress, TestNG, Allure, Robot, Cucumber.
Apache-2.0 -
Free MCP server and agent skill that runs, diagnoses and fixes failing Playwright tests (TypeScript and pytest), and proves each fix by re-running it. Flaky verdicts, finds the commit that broke a test, blocks fixes that check less, posts CI fixes as PR suggestions, accessibility and Web Vitals audits. MIT, no account.
npm MIT ★ 6 -
MCP server for Squally – read-only access to Playwright test runs, flaky tests and failures.
npm MIT -
TurnSignal for Playwrightno update data
Read-only Playwright CI results for agents: new vs known failures, flaky tests, test history.
npm -
Find which Playwright test failures are new: groups failures by cause, tracks run history and flaky tests. An MCP server for AI assistants.
MIT -
StackVitalsno update data
Known flaky tests, failing and slow CI, review flow, delivery and dependency risk from kept history.
pypi -
mcp-chaos-riggithub.com/typewise/mcp-chaos-rigupdated this year
A local MCP server that breaks on demand. Test your client against auth failures, disappearing tools, flaky responses, and token expiry.
npm MIT -
Playwright end-to-end testing MCP server — run, debug and inspect E2E tests from any AI agent: failure analysis, live DOM inspection, selector validation, visual diffs, flaky-test diagnosis.
MIT -
Open-source MCP server that gives AI agents the QA lead’s job: test strategy, quality gates, test generation and execution (Playwright, Cypress), flaky triage, release readiness. Judgments with evidence, deterministic guardrails, a replayable trace. Capabilities first, frameworks later.
MIT -
flakefindergithub.com/cognis-digital/flakefinderupdated this year
Flaky-test detector from CI history with quarantine suggestions
NOASSERTION -
Explains why a CI run failed: rule-based triage, flaky-test detection, MCP server and AWS Lambda webhook
MIT -
Run a project's tests and get small structured results over MCP: pytest, unittest, jest, vitest. Failures with trimmed tracebacks, rerun-failed, flaky detection, hard timeout that kills the whole process tree.
MIT -
Local aggregate test-history stability analysis without test names or raw result contents. Tools include analyze test history
npm MIT -
Turn Playwright's "flaky" label into a ranked, root-caused triage report. Zero dependencies.
MIT -
Your Playwright, Cypress or Selenium tests break when a selector moves — this finds the element again and rewrites the test. Deterministic: no LLM decides whether your build passes. Runs entirely on your machine, with a local MCP server for agents.
npm MIT -
Stop parallel tests from fighting over shared test accounts and environments. Exclusive, expiring leases with evidence.
npm Apache-2.0 -
MCP server exposing kinora test failures and history (Playwright, Vitest, Storybook) to coding agents
npm MIT -
Diagnose your GitHub Actions: flaky jobs, wasted minutes, slow steps, cache problems, and workflow anti-patterns — in one command, zero config.
go MIT ★ 3 -
Reproduce, isolate, and minimize software failures. Built for humans and coding agents.
npm MIT -
Read-only MCP server for AI-assisted root-cause analysis of TeamCity build failures
npm MPL-2.0 ★ 8 -
ci-triagegithub.com/clankamode/ci-triageupdated this year
Open-source CI failure triage for humans and agents — smart log parsing, flake detection, structured JSON, MCP server.
npm MIT -
Claude Code QA agent with memory, plus a read-only MCP server (verdict-qa-mcp on PyPI): baseline → delta runs (NEW/REGRESSED), a fact harness so the model judges while the system measures, hash-chained run history, flaky quarantine with expiry, and an exit-code release gate for CI. Ships six scored eval fixtures — misses published.
pypi MIT ★ 4 -
Proves software work: triages failing tests to a cause with evidence, says whether a test could ever fail, breaks your code to see if the tests notice, reads what a migration does to a live database, and gives one verdict on whether a change is done.
npm Apache-2.0 -
Ranks failed regression logs into a morning report: groups by first error, flags flaky failures, and suggests where to start. Includes an MCP server.
-
TestRail for AI agents: an MCP server, a CLI and a TypeScript library that answer QA questions in one call. Run reports, failures, flaky vs regressed, coverage gaps.
npm MIT