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. 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.
-
ai-test-agent-mcpgithub.com/ibne86/ai-test-agent-mcpupdated this year
—
★ 1 -
UniSat AI Kit MCP server
npm MIT -
Multi-agent AI pipeline (AutoGen + MCP) that auto-generates QA test scenarios and automation-ready test cases into Excel.
-
Un serveur MCP (Model Context Protocol) développé en Java pour tester les performances d'un autre client.
-
agentic-testing-mcpgithub.com/Jai-Gogineni/agentic-testing-mcpupdated this year
AI-driven testing using Model Context Protocol — context-aware verification, LLM steering, agentic workflows with Playwright
MIT -
ai-agent-seleniumgithub.com/learn-automated-testing/selenium-mcp-serverupdated this year
Node.js launcher for Selenium MCP Server - AI-powered browser automation with test agents
npm MIT -
The Wozniak coffee test as an embodied MCP game for AI agents
MIT ★ 1 -
Code-aware browser testing for AI coding agents. 14 MCP tools, CLI workflows, regression memory, and human-readable QA reports.
npm MIT ★ 18 -
AI-driven Universal QA Skills, MCP Server, Precision Testing (TIA), and Evals for all AI coding agents.
MIT -
agentic-test-generatorgithub.com/Hrushitha12/agentic-test-generatorupdated this year
5-agent AI system using CrewAI, MCP, and A2A Protocol to autonomously generate API test suites from OpenAPI specs — GPT-4o/Claude Sonnet via LiteLLM with LangSmith tracing
-
x402-test-mcpgithub.com/sansscott/x402-test-mcpupdated this year
MCP server: verify your AI agent can make real x402 payments — $1 test, signed diagnostic report
MIT -
Official MCP server for TestKase Test Management (formerly @testkase/mcp-server) — AI-powered test management for Claude, Copilot, and any MCP-compatible agent
npm MIT -
MCP server (TypeScript/Node.js) that exposes flake-detector, test-quality-linter, and llm-eval-harness as tools an AI agent can call — so Claude Code and other agents can check test health instead of guessing.
Apache-2.0 -
Playwright-style UI testing for Godot & Unity. One semantic automation layer for tests, CI, and AI coding agents via MCP.
npm MIT ★ 23 -
Open-source E2E testing an AI agent records for you. Plain-language tests, recorded once on your real app (web, desktop, SAP, Citrix, AI agents), replayed on every commit with zero LLM calls.
npm Apache-2.0 ★ 6 -
fixture_mcpgithub.com/BirajMainali/fixture_mcpupdated this year
MCP server for stateful API testing by AI agents.
npm MIT -
MCP server that lets AI coding agents autonomously test Chrome extensions through a real browser: 13 tools covering popups, storage, network, badges, and messaging. On npm.
npm MIT ★ 3 -
@neuraforge/loadtest-mcpgithub.com/vikisingh23/loadtest-mcpupdated this year
MCP server for load testing APIs. Run load tests, stress tests, and regression detection from any AI agent.
npm Apache-2.0 -
vibe-testingno update data
Code-aware browser testing for AI coding agents.
smithery -
MCP server for test-inventory: AI agents ask which Playwright, Vitest, Jest, Mocha, Jasmine, Cypress, WebdriverIO, node:test and Bun tests a project has, which are skipped and why, and which a change can affect, without running them.
npm MIT ★ 3 -
Indexes a Java Spring codebase into a context graph (code, OpenAPI specs, docs, config) and serves it to AI agents over MCP: what to mock, generated DTO fields, endpoints, existing tests, and the provider APIs a service calls, for unit and Specmatic contract tests.
MIT ★ 1 -
Comprehensive testing capabilities for AI agents with MCP integration
MIT -
qa-lab-agent-mcpgithub.com/Wesley-Gomes93/qa-lab-agent-mcpupdated this year
MCP-powered AI agent for QA — test generation, failure analysis, automation copilot
-
playwright-mcp-ai-testinggithub.com/Zain-Imam/playwright-mcp-ai-testingupdated this year
AI-augmented test automation — Playwright MCP server, agent-assisted authoring, documented case study, human-refined TypeScript suite.
MIT -
Manual testing hub: AI-authored test guides, per-platform test runs, MCP agent access. Self-hosted on AWS.
MIT -
MCP server for AI-orchestrated human QA testing. Let AI agents request real human testing of web applications.
npm ISC -
@kalisky/skargithub.com/kalisky/skarupdated this year
Skar turns a captured AI agent trace into a committed pytest regression test. MCP server + CLI. Use when a tool-using agent run fails and you want to lock the failure as an executable test.
npm MIT -
MCP server that runs Foundry tests and returns compact, structured failures for AI coding agents
npm MIT ★ 1 -
Taichi is a language-agnostic, plugin-driven test orchestration framework — run API, gRPC, UI, static, and regression tests with one CLI, extend via third-party skill plugins in any language, integrate AI agents for auto-fix loops, and ship JUnit/JSON/HTML reports.
Apache-2.0 ★ 1 -
@bearcreekai/testing-kx-mcpgithub.com/bearcreekai/testing-kxupdated this year
MCP server for KnowledgeExpert E2E testing platform. Run, generate, and manage Playwright tests from AI coding agents (Claude Code, Windsurf, VS Code Copilot).
npm UNLICENSED -
agent-identity-mcpactive
MCP server that gives an AI agent a disposable email address and a real UK phone number so it can test a signup/verification flow end to end.
npm MIT -
An acceptance test agent that keeps your AI agent team building to your taste. Works with Claude Code, Cursor, Codex and Windsurf.
npm Apache-2.0 ★ 16 -
Browser test harness on Playwright. Watch runs live, start, pause and review them on its own web page, and let your AI agents drive it through a CLI and MCP.
Apache-2.0 ★ 2 -
Deterministic UI knowledge graph for AI test agents. Verified Playwright locators from Angular and Next.js, queried over MCP.
MIT ★ 1 -
qantraactive
AI agent for end-to-end test automation: terminal UI, MCP server, skills and agents
npm MIT -
agent-regressgithub.com/Gaurav7974/agent-regressupdated this year
MCP server for regression-testing AI agents — deterministic checks (regex, exact-match, JSON schema, exit code), zero API keys required.
MIT -
OpenAPI testing and deterministic API fuzzing for AI agents—catch contract bugs before unsafe calls with local-first sealed plans, MCP, and replayable evidence.
mcpb Apache-2.0 ★ 2 -
MCP server for Live Test View — run Flutter widget tests and fetch frames for AI agents
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 -
@flakeytesting/mcp-servergithub.com/absence0760/project-flakeyupdated this year
MCP server for Flakey — lets AI coding agents query test results
npm MIT -
Local AI agent for Apache JMeter: turns test documents into requirements, runs the plan and judges every run with evidence (verdicts, baseline diff, Prometheus) - MCP built in.
Apache-2.0 ★ 2 -
Grafana-k6-performance-MCP-Servergithub.com/padmarajnidagundi/Grafana-k6-performance-MCP-Serveractive
Grafana k6 performance testing. One click installation. MCP, Agent, AI - Ready to use
MIT -
@kagura-run/mcpgithub.com/camie-tech/kagura-appupdated this year
MCP (Model Context Protocol) server for Kagura AI Cloud - Agentic Testing
npm MIT -
Let AI agents see, drive and test your iced (Rust GUI) apps over MCP: snapshot, click, type, assert and record regression flows.
cargo MIT -
mcp-internet-speed-testgithub.com/inventer-dev/mcp-internet-speed-testupdated this year
The MCP Internet Speed Test is a specialized Model Context Protocol (MCP) server that enables AI models and agents to perform internet speed measurements.
pypi MIT ★ 16 -
Common QA MCP — one product-neutral MCP that routes test-case lifecycle requests to Walnut or SimplifyQA for any AI client. Launch over stdio via npx; install the Walnut QA agent with `init-agents`.
npm MIT -
Drive a live Flutter app from an AI agent or CI: Semantics snapshots, gated taps and typing, screenshots, perf traces. No flutter_test harness, no test file between actions.
MIT ★ 3 -
@rocketshipai/mcp-servergithub.com/rocketship-ai/rocketshipupdated this year
MCP assistant for helping AI coding agents write better Rocketship tests
npm MIT -
@thinkbrowse/mcpgithub.com/dundas/mech-browseupdated this year
Let your AI coding agent test its own frontend work. Connects Claude Code, Cursor, and any MCP client to your real Chrome browser — real sessions, real cookies, no headless conflicts.
npm MIT -
AI-callable test automation as an MCP server: generate, run, triage and heal tests (Playwright/pytest) from any MCP-compatible AI agent.
MIT -
@breach-kit/agentupdated this year
BreachKit — AI security testing agent. MCP server that turns your coding agent into a pen tester. DAST, SAST, and SCA via Playwright.
npm Apache-2.0 -
test-maker-skillgithub.com/TeXmeijin/test-maker-skillupdated this year
Claude Code plugin + MCP skill for creating fill-in-the-blank and multiple-choice tests on Test Maker (test-maker.app) via AI agents.
MIT -
Lets AI coding agents write and run Appium mobile tests from Markdown prompts, using Appium MCP
MIT -
AI-driven testing platform with a conversational agent, visual API/Web/Android/JMeter cases, MCP, and local/server deployment.
MIT -
snapdrive-iosgithub.com/MasamiYamate/snapdrive-iosupdated this year
AI agents drive iOS Simulator to generate snapshot baselines and run visual regression tests.
MIT ★ 1 -
Official Mailsac MCP server: disposable test inboxes for AI coding agents (Claude Code, Cursor, VS Code)
npm MIT -
🌐 The Autonomous Eyes & Hands for AI Coding Agents. Browser testing, QA matrices, error telemetry, and Markdown reports via MCP & CLI.
npm MIT ★ 1 -
Self-hosted load testing on k6: model real user journeys, watch results live, find your breaking point and let AI agents draft tests over MCP.
Apache-2.0 ★ 3 -
Test websites the way customers use them: one real Chromium per test account, run from a CLI or by AI agents over MCP, with written-permission checks and client-ready reports.
Apache-2.0 -
zephyr-scale-mcpgithub.com/vilaabo/zephyr-scale-mcpupdated this year
MCP server for Zephyr Scale on self-hosted Jira Server/DC — full test management for AI agents: test cases, cycles, executions, plans, folders, attachments
npm MIT