MCP Servers
Connectors that give your AI agent hands — databases, browsers, email, payments, and every service in between.
✓ Official
31 companiesPublished by the companies themselves — pick one to see everything they ship.
modelcontextprotocol10 servers
google2 servers
googleapis3 servers
microsoft3 servers
azure3 servers
github1 server
awslabs34 servers
bytedance2 servers
stripe1 server
cloudflare2 servers
vercel5 servers
figma1 server
makenotion1 server
atlassian1 server
redis2 servers
elastic1 server
jetbrains1 server
ibm3 servers
getsentry3 servers
grafana1 server
hashicorp2 servers
firebase1 server
browserbase1 server
apify1 server
mendableai1 server
clickhouse1 server
neondatabase1 server
upstash2 servers
qdrant2 servers
e2b-dev1 server
exa-labs3 serversBrowser Automation
162 mcp servers
Debugger MCP Server
★ 1A development tool for real-time debugging, code quality monitoring, and AI insights for React/Next.js applications.
Playwright MCP Explorer
★ 1An intelligent tool that uses MCP to autonomously explore websites and generate Playwright tests from natural language descriptions.
Chromewright
★ 1Browser automation via Chrome DevTools Protocol
periscope-mcp
★ 1Website testing built for AI agents: 63 Playwright tools with hard assertions, auto form-fill, auth sessions, network mocking, and a11y/SEO/GEO + Lighthouse audits.
Integrated MCPs Guide
★ 1An integrated MCP server combining Azure DevOps, Gmail, Browser, and Gemini AI functionalities on a Node.js server.
Smithery Reference Servers
★ 1A collection of reference implementations for Model Context Protocol (MCP) servers in Typescript and Python, demonstrating MCP features and SDK usage.
Micromanage
★ 1A server for managing sequential development tasks with configurable rules using external .mdc files.
DevServer MCP
★ 1Manages development servers for LLM-assisted workflows, offering programmatic control through a unified TUI and experimental browser automation via Playwright.
Agent Engineering Bootcamp MCP
★ 1A server providing setup guidance for students learning agent development, with support for both Python and TypeScript.
Clelp MCP Server
Discover and rate 1,700+ MCP servers and AI agent skills with community ratings from real usage.
Sapiom
One API key gives agents access to 80+ tools: web search, deep search, browser automation, screenshots, 400+ LLM models, image generation, text-to-speech, sound effects, and phone verification. Pay-per-use with spend governance built in.
BerryRAG
A local RAG system with Playwright MCP integration for Claude and OpenAI embeddings, using local storage.
Model Context Protocol servers
A collection of reference server implementations for the Model Context Protocol (MCP) using Typescript and Python SDKs.
PlanWright
Objective-native planning board for agent-led development
Test Automator
An LLM-powered server for automating unit, integration, E2E, and API tests.
MCP Playwright Server
Automate web testing and tasks by connecting Claude Desktop with Playwright.
Tesults MCP
Connect AI agents to your test results, failures, flaky tests, and regressions across Playwright, Jest, Pytest, Cypress and more.
Playwright IA: Midscene.js
Automate Playwright flows using natural language with Midscene.js and AI.
MCP TUIKit
A headless terminal and tmux interaction server for Model Context Protocol.
MCP Servers
A collection of MCP servers for browser automation and database interaction, supporting Puppeteer, Postgres, MySQL, and Parquet.
flakiness-knowledge-graph-mcp
Builds a knowledge graph of flaky tests from Playwright run history
Safari MCP
The Safari MCP server gives your agent the ability to know how your code actually renders in the browser by connecting it to a Safari browser window
Metro MCP
A plugin-based MCP server for React Native runtime debugging, inspection, and automation. Connects to Metro bundler via Chrome DevTools Protocol — no app code changes needed for most features.
T-IA Connect
A Model Context Protocol (MCP) bridge to programmatically control Siemens TIA Portal (PLC, blocks, tags, and HMI).
GhostQA
GhostQA sends AI personas through your application — they look at the screen, decide what to do, and interact like real humans. No test scripts. No selectors. You describe personas and journeys in YAML, and GhostQA handles the rest.
tactual-mcp
Screen-reader navigation cost analyzer that measures the actual navigation effort for assistive-technology users by building a weighted graph from Playwright accessibility snapshots and scoring each target under real assistive-technology profiles (NVDA, JAWS, VoiceOver, TalkBack, generic mobile).
Chrome Debug MCP
This MCP allows you to record browser interactions with a chrome extension that include screenshots and console logs. The data is then saved to a local database that feeds the data to an AI system like claude code to search.
BCMS MCP
Give me a one - two sentence description of the BCMS MCP # MCP The BCMS Model Context Protocol (MCP) integration enables AI assistants like Claude,...
dr-mcp
Clean and audit messy MCP setups: stale servers, unused tools, context-heavy MCPs, outdated packages, and safe repair plans.
playwright-spatial-layout-mcp
Geometric vision for AI agents: bounding boxes, occlusion, viewport reflow