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.
-
responsive-tester-mcpactive
Model Context Protocol (MCP) Server for Responsive Tester - Multi-Screen Responsive Web Simulator & Testing Extension
npm MIT -
MCP tool for browser inspection, element selection, interactive messaging, and responsive testing
npm MIT -
Production-grade Browser Inspection & Responsive Testing MCP Server. Inspect websites, test across viewports, detect layout overflow, capture screenshots, and run audits via Playwright & MCP.
MIT -
mcp-testing-toolsgithub.com/rog0x/mcp-testing-toolsupdated this year
MCP server for testing: generate test cases, create mock data, mock API responses, analyze test coverage, generate assertions Install: npx @rog0x/mcp-testing-tools
MIT -
The most complete MCP server for API testing. 27 tools: requests, assertions, flows, OpenAPI, mock data, load testing, collections, environments, cURL export, response diffing. Zero config, zero dependencies.
npm MIT ★ 13 -
MCP server that calls your real API and checks the response against your OpenAPI spec — contract testing, auth presets, spec diffing, and health checks for Claude Code, Cursor, and Windsurf.
npm MIT -
Production-grade MCP server for Xray Cloud Test Management API with token-optimized TOON responses
npm Apache-2.0 -
OpenAPI spec parsing, test generation, live endpoint testing, and response validation
npm MIT -
A read-only MCP portfolio example with tenant filtering, minimal responses and tested API failure boundaries.
NOASSERTION -
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 -
babel_elastic_aigithub.com/builtbyraman/babel_elastic_aiupdated this year
Babel: Kibana-native SIGMA detection engineering with an AI assistant — author, convert, test & deploy, aligned to incident response and MITRE ATT&CK.
NOASSERTION -
Hierarchical Bayesian MMM, geo matched-market tests, spot-level TV response and a harmonization layer, with a results API and MCP server. Python, NumPyro, Postgres. Synthetic data.
MIT -
🔌 Exposes API testing over MCP — endpoint validation, response schema checks, load testing, OpenAPI compliance. MIT.
npm MIT -
A test of responses from a Function App
npm MIT -
A minimal Model Context Protocol (MCP) server that echoes back client messages. Designed for testing, debugging, and demonstrating MCP integrations with simple request-response behavior.
MIT -
The actual implementation battle tested your ai aisstant loves to use to provide accurate and grounded responses based on trusted sources.
★ 2 -
mcp-agent-toolkitgithub.com/shubham0086/mcp-agent-toolkitupdated this year
Production MCP server toolkit: shared blackboard, SCAR failure memory, LLM response cache. Node.js 22+, node:sqlite, 13 tests.
★ 1 -
MCP server (stdio) for testing REST APIs: all HTTP methods, custom headers, auth, credential masking, response size limits, SSL toggle, SOCKS/HTTP proxy
npm MIT -
Read-only MCP server for NYC building violations (DOB, ECB, HPD) from NYC Open Data, with safe queries, bounded responses, and offline tests.
MIT -
Security review tooling for Model Context Protocol deployments. Probes a live server's OAuth authorization surface and records the request and response behind every finding, or scans a repository's source. Reports name what was not tested.
pypi MIT ★ 7 -
An MCP client and a retrieval MCP server over a production RAG corpus. Typed responses instead of JSON strings, so a drifting tool schema fails loudly instead of returning a confident wrong answer. 83 tests, 4 ADRs.
MIT -
@eddym06/custom-chrome-mcpgithub.com/eddym06/devtools-advance-mcpupdated this year
Cross-platform Chrome MCP with real-time request interception, response modification, network capture, HAR recording/replay, accessibility testing, anti-detection, and 91 tools. Includes smart workflows for common tasks. Works on Windows, Mac, and Linux.
npm MIT -
Cross-platform Chrome MCP that runs on a persistent clone of your real Chrome profile (session/logins carried over) with real-time request interception, response modification, network capture, HAR recording/replay, accessibility testing, stealth mode, con
npm MIT -
Mobile preview for developers and AI agents. See any website the way it looks on a real iPhone, iPad, Android phone or MacBook — and let an AI agent see and drive that same window over MCP. Responsive testing with device frames measured in millimetres. Windows and macOS apps, VS Code extension, MCP server.
mcpb NOASSERTION ★ 1 -
Badgr — GPU Compute, AI Model Deployment & Agent Executionno update data
**Run GPU workloads, deploy AI models, access inference APIs, and execute AI agents using Badgr's MCP server.** Badgr is an AI compute and workload execution platform for developers, coding agents, and AI assistants. Run workloads on cloud GPUs or compatible customer-owned GPUs (BYO GPU), with cost controls, execution logs, and verified results. **What can Badgr do?** - **GPU Compute / AI Workloads:** Run Python scripts, machine learning jobs, batch inference, and supported ComfyUI workflows. - **AI Model Deployment:** Deploy and serve LLMs using compatible runtimes such as vLLM and SGLang. Get a verified, OpenAI-compatible inference endpoint. - **AI API / LLM Inference:** Make AI API requests with response validation, supported fallback routing, and bounded execution. - **AI Agent Execution:** Launch coding and testing agents, run tasks, check acceptance criteria, and retrieve execution receipts. **Key features:** Cloud GPU execution, BYO GPU support, model serving, AI agent jobs, workload verification, execution logs, cost limits, and deployment management. Connect Badgr to your MCP-compatible AI assistant to execute real workloads instead of just generating instructions. Get started: https://aibadgr.com **Requires a Badgr API key. GPU workloads and other paid execution may incur usage charges.**
smithery -
api-testing-mcpupdated this year
MCP server for API testing
npm MIT -
@responsive-tester/mcpactive
Drive Responsive Tester from your terminal AI (Claude Code, Cursor, Continue).
npm MIT -
viewpo-mcpgithub.com/littlebearapps/viewpo-mcpupdated this year
MCP server for Viewpo — gives AI coding assistants eyes into responsive viewport rendering
npm MIT -
Servidor MCP que emula teléfonos, tablets y otras pantallas abriendo el navegador local, para que cualquier agente capture y audite layouts responsive
npm MIT -
⚡ Lightning-fast MCP browser dev tool. Navigate → Get instant structured data. No screenshots needed! Puppeteer: 📸 → CSS selectors → JS eval. Supapup: semantic IDs ready to use. 10x faster, 90% fewer tokens.
npm MIT -
refractgithub.com/valternunez/refractupdated this year
Agent-first responsive screenshots — render a URL at N viewports, get images + structured findings. MCP server + CLI + Node library on Playwright.
MIT -
panescope-mcpactive
MCP server for Panescope: lets AI coding agents open pages on many devices, take screenshots, read console errors, run accessibility and responsive audits, and interact with the page.
npm UNLICENSED -
MCP server for dynamic Playwright browser pool management — 75 tools, 28 built-in UI audits, 42 CLI commands, 143 device presets, golden profile auth. Built for Claude Code, Cursor, and AI-assisted web development.
MIT -
api-tester-mcpgithub.com/anomalyco/api-tester-mcpupdated this year
Ultra-lightweight API tester exposed as MCP tools — JSON in, structured response out
npm MIT -
Compare websites side by side in real Chromium, WebKit, and Firefox on macOS, with an inspector and a CLI/MCP server for coding agents
MIT -
Real phone, tablet and laptop frames floating over your code, with an MCP server your coding agent can drive. Mac and Windows.
-
Agentic Work Assist - Production-ready MCP server with Constitutional AI Meta-Prompting Enhancement System featuring real-time prompt optimization, automated pattern recognition, constitutional AI-validated prompt evolution, A/B testing framework, compreh
npm MIT -
Send requests, understand responses, and keep your workflows together in a fast native desktop app.
-
Protótipo educacional de capacitação responsável em IA com dados sintéticos, testes automatizados e MCP read-only.
NOASSERTION -
Turn Burp traffic into report-ready screenshots from your AI chat — real request/response evidence, highlights, diffs, and secrets redacted by default. Never a fake image.
GPL-3.0 -
ProdRescuegithub.com/BashaarJavaid/ProdRescueupdated this year
Autonomous self-healing SRE agent pipeline that detects production incidents, diagnoses root cause, writes and tests a patch, and opens a PR — built with LangGraph, MCP, and a sandboxed QA harness.
MIT -
Free, open-source responsive design tester: see a site on 290+ phones, tablets and desktops at once, find layout bugs on each, and check pages from the CLI or AI agents (MCP).
npm ★ 3 -
GenClass Runtime: a 10 MB in-browser model that detects race conditions, stale responses and duplicate requests in web apps; opt-in guard mode can prevent some of them. npm i @genclass/runtime
npm Apache-2.0 ★ 11 -
Self-hosted REST & SOAP mock server in one Java jar — no external DB, built for offline intranets. Multi-team isolation, multi-scenario responses, dynamic variables, optional AI & MCP. 内网接口 Mock:单 jar 离线部署,多团队隔离、多场景响应、动态变量,可选 AI 与 MCP。
MIT -
Check LLM responses against the output rules your application depends on, before changing a model, prompt, schema or provider. Also flags retired model IDs in your code. Local CLI, GitHub Action and MCP server; no third-party runtime dependencies.
pypi MIT ★ 3