Search MCP servers
Filter by capability, transport, auth, language, and verification.
18 results
Lets coding agents drive a real Chrome: automate input, read console and network, record performance traces.
Automate your existing browser with AI using your real profile, logged-in sessions, and stealth fingerprint.
Lets agents read LinkedIn profiles, companies, jobs and messages through your own logged-in browser session.
Run SQL over files, databases, and 40+ apps (GitHub, Notion, Chrome, Todoist) — and expose them to LLMs via MCP.
Computer-use MCP server that automates Windows desktop and browser apps via the accessibility tree.
Selenium WebDriver MCP server — cross-browser automation for Chrome, Firefox, Edge, and Safari.
Point at browser DOM elements with Option+Click and feed them as context to agentic coding tools via MCP.
Control Figma from the terminal or as an MCP server — full read/write: create shapes, text, components, render JSX, export images.
Community Puppeteer MCP server that can launch a browser or attach to an existing Chrome window.
Automate and inspect Firefox via WebDriver BiDi (Selenium) from any MCP client.
Give Claude Code a browser that thinks — delegate agentic web browsing and deep research to Perplexity Comet.
Native Safari browser automation for AI agents on macOS — 80 tools, your real logged-in browser, no Chrome.
Semantic code search & navigation for AI agents — jump to the exact functions and chunks instead of reading whole files.
Autonomous browser automation for Claude Desktop via Playwright, plus an HTTP API client.
Give AI agents eyes and hands on any desktop via native accessibility APIs — no vision model required.
Give AI agents control of your real Chrome browser with existing sessions, cookies, and logins.
Drive Chrome, Firefox, Edge, Safari and iOS/Android apps with WebDriverIO, locally or on cloud devices.
Session-token Slack access for AI agents — no OAuth, no app registration, 21 tools, one command.