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 metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.
npm Apache-2.0 ★ 69 -
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 -
MCP server exposing Cypress end-to-end test execution to LLM agents.
MIT -
OpenTestergithub.com/kznr02/OpenTesterupdated this year
AI-Drived end-to-end test platform
pypi MIT ★ 29 -
qantraactive
AI agent for end-to-end test automation: terminal UI, MCP server, skills and agents
npm MIT -
MCP server for AI-driven REST API end-to-end testing — use-case oriented, safe, efficient
cargo MIT OR Apache-2.0 -
@kuste/runneractive
Run end-to-end tests written as intentions, not selectors. CLI and MCP server.
npm UNLICENSED -
@iflow-mcp/debugg-ai-mcpstale
Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.
npm Apache-2.0 -
Use this project to verify that your MCP server is properly configured and to test a simple end-to-end integration workflow.
npm MIT ★ 1 -
Saffron for Claude Code: language server, MCP server and agent skill for .saffron end-to-end tests, as one plugin
-
MCP for End to End golang testing with DAP debugger, CURL, and PGSQL
MIT ★ 1 -
@allenpan2026/harshjudge-mcpgithub.com/huskydanny/harshjudgeupdated this year
AI-native E2E testing orchestration MCP server for Claude Code. Create, run, and manage end-to-end test scenarios with visual evidence capture.
npm MIT -
@allenpan/harshjudge-mcpgithub.com/anthropics/harshjudgeupdated this year
AI-native E2E testing orchestration MCP server for Claude Code. Create, run, and manage end-to-end test scenarios with visual evidence capture.
npm MIT -
MCP server for the Ghost Inspector API — lets any MCP-capable agent triage, validate and safely repair end-to-end browser tests
npm MIT -
One MCP server, skill pack, and CLI for end-to-end Android development with AI agents: devices, UI tests, Supabase backend tests, localization lint, gated releases.
MIT -
Host-driven end-to-end testing for Android, in Kotlin or Python: one server per machine, a separate on-device driver, JUnit 5 and pytest clients, and an MCP server for coding agents.
Apache-2.0 ★ 2 -
Todo app built end to end by AI coding agents from Linear tickets, with automated tests, 4 GitHub Actions workflows and a custom MCP server that lets LLMs answer questions about the codebase.
-
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 MCP server that enables AI agents to perform real end-to-end testing of Minecraft server plugins using bots and server introspection.
npm MIT ★ 2 -
AI-leveraged end-to-end web testing: Playwright (Chromium/Firefox/WebKit) driven by Claude over MCP. Desktop app, 7 CLIs, 51 MCP tools, self-healing selectors, a11y/perf/SEO/PWA audits.
MIT -
MCP server that gives Claude safe tools over a real web app, tested end to end through a real MCP client. Includes prompt-injection guardrails and 5 reusable Claude skills for QA.
NOASSERTION -
KaDeep Studios CLI and releasegate: AI end-to-end testing from your terminal, CI/CD and coding agents (MCP). Run tests on web, mobile and desktop and get a go / no-go for every release.
npm Apache-2.0 ★ 1 -
midjourney-mcpgithub.com/0xj7r/midjourney-mcpupdated this year
Personal MCP server example for Midjourney via Discord, built in TypeScript with typed tool handlers, stdio transport, and end-to-end MCP tests.
MIT -
tesseract-voice-aigithub.com/jmanhype/tesseract-voice-aiupdated this year
🎯 Tight end-to-end MCP+GraphQL control plane with real-time test orchestration, dry-run workflows, and interactive confirmation dialogs. Features Strawberry GraphQL, Apollo Router federation, and Next.js interface.
★ 1 -
@ia-qa/qa-discoveryactive
Find out what is in a web app before you test it — every page, form, field and API call it serves, the pages your end-to-end suite never visits, and starting Playwright tests for them. Deterministic and local, with an MCP server for agents.
npm MIT -
The definitive Spotify MCP server — full non-deprecated Web API coverage, paginated everything, podcast-first, tested end to end
npm MIT ★ 1 -
MCP server that gives AI assistants ParlIQ's UK select committee evidence, Hansard and votes as 14 tools, with live end-to-end tests.
MIT -
Stage 3 — MCP server (FastMCP) exposing a secure record_reservation tool: token auth, input sanitisation, path confinement and file locking. 57 tests including a guarded stdio end-to-end test.
-
Complete AWS Security AgentCore Solution - 7-layer architecture with MCP Server, AgentCore Runtime, Gateway, Bedrock Agent, and React frontend. Production-ready deployment with OAuth, parameter mapping, and end-to-end testing.
-
Task environments for AI agents working on .NET apps, as an MCP server: raise the app with its services on Nomad, call its API, read its logs, run its end-to-end tests, one environment per task. Native AOT ready.
MIT -
Run your coding agent's tests and commands on machines you own: a sandboxed, signed job slot instead of an SSH login, end-to-end encrypted. CLI, runner and MCP server.
npm MIT OR Apache-2.0 -
LitterBoxgithub.com/BlackSnufkin/LitterBoxupdated this year
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
pypi GPL-3.0 ★ 1,571 -
MCP_SERVER_WITH_PLAYWRIGHT_AND_CLAUDEgithub.com/nikhilfufu/MCP_SERVER_WITH_PLAYWRIGHT_AND_CLAUDEupdated this year
An MCP server built in C# that exposes QA automation tools (like browser login) to AI clients. It uses Playwright for browser automation and ExtentReports for HTML reporting with screenshots, allowing AI agent (Claude) to run and inspect real end-to-end tests.
-
End-to-end urban mobility ML platform: 90M Citi Bike starts, six-model forecasting, LangGraph/MCP SQL agent, A/B testing, Docker, GCP & MLOps.
MIT -
Google AI Studio inside Claude — Gemini, Nano Banana images, Veo 3.1 video with audio, and TTS as a zero-dependency MCP server, with a mocked end-to-end test suite
MIT -
Read-only MCP server over the Toronto open data warehouse: curated tools plus sqlglot-checked SQL, a least-privilege role and read-only transactions, tested end to end over MCP
MIT -
agent-identity-mcpno update data
Give an AI agent a throwaway email address and a real phone number for SMS so it can test signup and verification flows end to end, without a human relaying codes. Wraps receivemail.dev (disposable email) and sms-florin (rentable phone numbers) in one MCP server.
smithery -
Self-hosted apps you run on your own machine, each tested end to end on a real Edgible serving device every week: Gitea, Immich, Vaultwarden, Umami, an MCP bridge, and more
MIT -
MCP server and client in Python: a FastMCP document server with tools, resources and prompts, and the client a Claude CLI chat uses to reach it. Built from the starter of Anthropic Academy's Introduction to Model Context Protocol course, with bug fixes and 15 end-to-end tests.
-
Reference deployment of a governed AI stack: LLM gateway, MCP evidence server and multi-agent service as hardened containers, with secrets, Prometheus monitoring and alerts, pinned versions, a runbook and an end-to-end test in CI.
MIT -
DOKU Gemini MCP Plugin oku-gemini-mcp is an advanced AI plugin and Model Context Protocol (MCP) server for Google Antigravity, Gemini, Claude Desktop, and Cursor. It equips AI coding assistants with end-to-end capabilities to scaffold, configure, test, sign, and maintain
MIT ★ 2 -
Zero-trust AI control plane: strict stdio MCP server, MCP security gateway (JWT + RBAC), streaming PII guardrail, and a rate-limited failover LLM router, with an end-to-end demo and 348 tests.
-
Local stdio Model Context Protocol (MCP) server for AI coding agents, wrapping the packaged vouchfx end-to-end integration-testing CLI. Advertises eighteen tools — validate_suite, list_step_types, describe_step_type, search_docs, plan_coverage, scaffold_suite, run_suite, explain_run, diagnose_run, explain_diagnostic, get_schema, normalize_suite, get_run_events, get_run_status, cancel_run, list_runs, get_step_timeline, get_run_artifacts — plus a vendored-documentation MCP resource pair and a per-code diagnostic catalogue resource, so an agent can validate, normalize, and scaffold .e2e.yaml suites, browse the step-type catalogue and the language's own JSON Schema, plan a suite set's coverage and gap findings, run suites with a taxonomy-faithful verdict, poll, list and gracefully cancel those runs, diagnose a run's JSON Lines event stream, page that stream's raw events, inventory what a run left behind, obtain Fail-only Healer patch proposals, and look up any VFX-* code's meaning and fix
nuget Apache-2.0 -
electron-test-mcpgithub.com/lazy-dinosaur/electron-test-mcpupdated this year
MCP server for testing Electron apps via Playwright - supports both CDP connection and direct launch
npm MIT -
qaclawgithub.com/vlddlv/qaclawupdated this year
Autonomous QA agent - runs browser-based tests via MCP
npm MIT -
Real browser automation for AI agents
npm NOASSERTION ★ 8 -
MCP server for React Native and Expo development
npm SEE LICENSE IN LICENSE -
Fastest cross-platform E2E Automation for Mobile & Web
Apache-2.0 ★ 103 -
Assertline's hosted MCP server: find your recorded web tests, run them and read step-by-step results. Instructions only.
MIT -
@democratize-quality/mcp-servergithub.com/uppadhyayraj/democratize-quality-mcp-serverupdated this year
MCP Server for democratizing quality through browser automation and comprehensive API testing capabilities
npm AGPL-3.0-or-later -
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
npm MIT ★ 20 -
@teapotz/electron-mcpupdated this year
Electron UI automation via Playwright
npm -
@teststream/cliactive
Teststream from a terminal, a pipeline or a coding agent: runs, tests, branches, and an MCP server
npm Apache-2.0 -
Autonomous Telegram-bot QA for Claude Code: snapshot-test dialogs over MTProto, specs from source code, zero tokens at run time.
MIT ★ 2 -
@gowthaman-ravi/pw-recordergithub.com/gowthaman-ravi/playwright_mcpupdated this year
Playwright-based manual-action recorder with right-click expectations, exposed via CLI and MCP for LLM-driven test generation.
npm MIT -
@assert-click/mcpgithub.com/pixel-funnel/assert-click-mcpupdated this year
Run AI-powered E2E tests from plain Markdown. Generate scenarios, execute Playwright tests, and inspect results — all from your AI coding agent.
npm MIT -
Human-like AI QA testing for any web app — Claude Code & Codex plugin, MCP server and CLI. Playwright drives a real browser like a person, finds UI, accessibility and permission bugs, and re-tests only what changed. Zero AI tokens per run.
MIT -
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
npm NOASSERTION ★ 857 -
API tests your AI writes and your CI runs: YAML files in your repository, one native binary, no account. A Postman alternative with a VS Code extension, a browser app and an MCP server for coding agents.
oci GPL-3.0 ★ 3 -
A Model Context Protocol (MCP) server for UUV - a solution to facilitate the writing and execution of E2E tests understandable by any human being(English or French) using cucumber(BDD) and cypress or playwright.
npm MIT