Code-only MCP servers — agent-tools.cloud

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.

@mseep/server-test-runner
stale

A Model Context Protocol (MCP) server for running and parsing test results from multiple testing frameworks. This server provides a unified interface for executing tests and processing their outputs, supporting:

npm
@matware/e2e-runner

github.com/fastslack/mtw-e2e-runner
updated this year

E2E test runner using Chrome Pool (browserless/chrome) with parallel execution

npm Apache-2.0
mtw-e2e-runner

github.com/fastslack/mtw-e2e-runner
updated this year

JSON-driven E2E test runner with parallel execution, Chrome pool, and Claude Code MCP integration

Apache-2.0 ★ 7
agent-in-browser

github.com/Gwakko/agent-in-browser
active

A real browser for any AI agent, model or test runner — MCP server + CLI + scenario runner in one Go binary. Chrome/Edge/Brave via CDP, Firefox via WebDriver BiDi.

MIT
meta-labautomation

github.com/embetrix/meta-labautomation
active

OpenEmbedded/Yocto layer for embedded lab automation with CI/CD runners, flashing tools, power control, hardware testing, remote access and Agentic AI automation.

NOASSERTION ★ 18
Motus

github.com/DataficationSDK/Motus
active

Extensible browser automation and testing framework for .NET. Communicates directly with Chromium (CDP) and Firefox (WebDriver BiDi) over WebSocket, no Node.js dependency. Source generated protocol bindings, Roslyn analyzers, a test recorder, a Blazor visual runner, and an MCP server for AI agents, all built on public plugin interfaces.

MIT ★ 16
TestDesk

github.com/thecodingrasta/TestDesk
active

Cross-platform desktop test runner and MCP server. Find, run and debug tests in multiple projects at once, with a separate queue and history for each. Supports Go, .NET, Playwright, Vitest, Jest, pytest, Cargo, Maven, Gradle and Cypress. AI agents like GPT, Gemini and Claude can run and diagnose tests over MCP.

GPL-3.0
Pare

github.com/Dave-London/Pare
active

Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.

npm MIT ★ 141
odoo20-claude-toolkit

github.com/mediafish-agency/odoo20-claude-toolkit
active

Claude Code plugin for Odoo 20: version-verified skills + MCP server (source index, Odoo 19→20 validator, odoo-bin test runner, JSON-2)

LGPL-3.0
mk-qa-master

github.com/kao273183/mk-qa-master
active

Stable since v1.0.0 — MCP server + cross-host agent skill (Claude Code / Codex / OpenClaw / Hermes) for QA testing across pytest / Jest / Cypress / Go / Maestro / Schemathesis / Newman, plus v1.1 Edge AI Runner (RTSP + YOLO). 22 frozen tools, bilingual EN/zh-TW QA knowledge, AI Visual Challenge Solver (reCAPTCHA / hCaptcha), OWASP API Top 10 (2023) scanner, universal qa_plan + verify bookend across 5 core tools (AI 測試大師)

pypi MIT
MCP-Server-Extension-for-Jetbrains-IDEs

github.com/TropinAlexey/MCP-Server-Extension-for-Jetbrains-IDEs
active

Rider plugin for the JetBrains MCP Server: test runner, SQL consoles, tool windows, IDE state, run configs, NuGet and profiling tools for AI agents — complementing the built-in tools

MIT
lunar-mcp

github.com/illocean/lunar-mcp
active

Eclipse IDE MCP server: a Model Context Protocol server that lets AI coding agents such as Claude Code, Codex and OpenCode build, run, debug and test Java projects inside a live Eclipse workspace, via JDT, launch configurations and the JUnit runner.

MIT
zeno-mobile-runner

github.com/johnmikel/zeno-mobile-runner
updated this year

Deterministic mobile UI checks for AI coding agents. One Zig binary drives real iOS/Android devices, returns a typed pass/fail, and writes a replayable trace you can gate a merge on. No LLM inside.

MIT ★ 5
Playwright-Automation-Framework-POC

github.com/BakkappaN/Playwright-Automation-Framework-POC
stale

Playwright MCP Server & Playwright-Automation-Framework-POC

★ 1
cli-test-summary

github.com/jantcz/cli-test-summary
active

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
yatt-ts

github.com/josvaal/yatt-ts
active

Highly configurable YATT MCP server library: spin up your own UI-testing MCP server (35 tools, Playwright engine, headless-first) with strict, typed configuration for paths, HTTP transport, auth, permissions, sessions and retention.

npm MIT
ai-dev-cli-tools

github.com/MatthiasLew/ai-dev-cli-tools
active

Cross-platform CLI toolkit and local MCP server for AI coding agents. Optimizes context windows and token consumption by turning raw outputs into compact, deterministic Markdown/JSON reports.

MIT ★ 3