Search MCP servers
Filter by capability, transport, auth, language, and verification.
17 results
Microsoft's official browser-automation MCP using Playwright's accessibility tree (no vision model).
Structured step-by-step reasoning tool for breaking problems into revisable thought sequences.
Background computer-use MCP server that drives native macOS, Windows, and Linux desktop apps without stealing focus.
Official AWS Labs server that lets agents call any AWS API via the AWS CLI surface.
macOS screen capture, AI visual analysis, and full GUI automation for AI agents.
Computer-use MCP server that automates Windows desktop and browser apps via the accessibility tree.
Community server to manage Railway.app projects, services, and deployments via your agent.
Connect Claude Desktop to any Hugging Face Space (Gradio app) with minimal setup — image gen, vision, TTS, STT and more.
Local computer-vision image recognition and editing tools for AI assistants — crop, detect, OCR, remove background, all on-device.
Bridge to query multiple LLMs and CLI coding agents as AI "ducks" for diverse perspectives.
Manage Heroku apps, dynos, add-ons, pipelines, and Postgres from your AI agent via the official Heroku CLI.
Prisma's official MCP: run migrations, provision Prisma Postgres, execute SQL and manage backups from your agent.
MCP server for xAI's Grok API: agentic tool calling, image/video generation, vision, and file support.
Manage Redis Cloud subscriptions, databases, and tasks with natural language.
Give AI agents eyes and hands on any desktop via native accessibility APIs — no vision model required.
Universal MCP server that drives your test suite end-to-end: run pytest/Jest/Cypress/Go/Maestro, analyze pages, generate tests, and advise.
Local MCP server for surgical, formatting-preserving edits to existing Word (.docx) and OpenDocument (.odt) files.