Chrome
The Chrome MCP Server transforms your Chrome browser into an automation tool controlled by AI assistants, such as Claude and Cursor.
This Chrome extension-based approach uses your existing browser environment with all your login sessions, configurations, and preferences intact.
Features
- 🤖 Multi-AI Compatible: Works with any LLM or chatbot client that supports MCP
- 🌐 Native Browser Integration: Uses your existing Chrome browser with all settings and login states
- 🔒 Full Privacy Control: Runs completely local with no external data transmission
- ⚡ High-Speed Connection: Streamable HTTP protocol for fast communication
- 🔗 Cross-Tab Operations: Manage and interact with multiple browser tabs simultaneously
- 🧠 AI-Powered Search: Built-in vector database for semantic content discovery across tabs
- 📊 Smart Content Analysis: Intelligent text extraction and similarity matching capabilities
- 📸 Advanced Screenshots: Element-specific and full-page capture with custom dimensions
- 🌐 Network Monitoring: Real-time request capture with response body analysis
- 🎯 Interactive Automation: Form filling, clicking, and keyboard input simulation
- 📚 Data Management: History search, bookmark organization, and tab management
- 🚀 SIMD Optimization: WebAssembly acceleration for 4-8x faster vector operations
- 🛠️ 20+ Browser Tools: Comprehensive API coverage for browser automation tasks
Use Cases
- Development Workflow Automation: Let AI capture network requests during testing, take element screenshots for documentation, and analyze API responses automatically while you focus on coding
- Research and Content Analysis: Have your AI assistant search through dozens of open tabs, extract relevant information, and create summaries from multiple sources without manual tab switching
- Quality Assurance Testing: Automate screenshot comparisons, form filling scenarios, and cross-browser functionality testing using your actual browser environment with real user data
- Data Collection and Monitoring: Set up AI-driven web scraping workflows that respect your existing login sessions and can adapt to page changes using semantic content analysis
How to Use It
1. Visit the GitHub releases page and download the latest extension package.
2. Install the global bridge package:
npm install -g mcp-chrome-bridgepnpm install -g mcp-chrome-bridge3. Load the Extension in your Chrome browser
- Open Chrome and navigate to
chrome://extensions/ - Toggle “Developer mode” to enabled
- Click “Load unpacked” and select your downloaded extension folder
- Click the extension icon and select “Connect” to view the MCP configuration
4. Add this configuration to your Claude Desktop MCP settings:
{
"mcpServers": {
"streamable-mcp-server": {
"type": "streamable-http",
"url": "http://127.0.0.1:12306/mcp"
}
}
}Available Tools
Browser Management Tools
get_windows_and_tabs: List all browser windows and their tabschrome_navigate: Navigate to URLs with viewport controlchrome_close_tabs: Close specific tabs or entire windowschrome_go_back_or_forward: Browser history navigation
Visual Capture Tools
chrome_screenshot: Advanced screenshot functionality with element targeting and full-page support
Network Analysis Tools
chrome_network_capture_start/stop: Monitor web requests using Chrome’s webRequest APIchrome_network_debugger_start/stop: Deep network analysis with response body capturechrome_network_request: Send custom HTTP requests through the browser
Content Discovery Tools
search_tabs_content: AI-powered semantic search across all open browser tabschrome_get_web_content: Extract HTML and text content from web pageschrome_get_interactive_elements: Identify clickable elements on pages
Interaction Tools
chrome_click_element: Click elements using CSS selectorschrome_fill_or_select: Fill forms and select dropdown optionschrome_keyboard: Simulate keyboard input and shortcuts
Data Management Tools
chrome_history: Search browser history with time-based filterschrome_bookmark_search: Find bookmarks using keyword searchchrome_bookmark_add: Create new bookmarks with folder organizationchrome_bookmark_delete: Remove existing bookmarks
FAQs
Q: Does this send my browser data to a third-party server?
A: No, the server operates completely on your local machine. All communication happens directly between the Chrome extension and the AI client on your computer, ensuring your data stays private.
Q: Why is the mcp-chrome-bridge package necessary?
A: The bridge serves as a local intermediary. Chrome extensions have security restrictions that prevent them from directly opening network ports that other applications can connect to. The bridge listens for connections from your AI client and safely relays commands to the extension.
Q: How is this better than a Playwright-based MCP server?
A: The main advantage is that Chrome MCP Server uses your personal browser instance. Playwright-based servers launch a new, clean browser process for each session. This means you have to log in to websites every time. With this server, the AI can automate tasks on sites where you’re already logged in, using your existing cookies and settings.
Q: Can I use this with AI assistants other than Claude?
A: Yes, any AI system that supports the Model Context Protocol can connect to this server. The server is model-agnostic and works through the standard MCP interface.
Latest MCP Servers
YouTube MCP Server
SEO Research
Cursor n8n
Featured MCP Servers
Apify
Blueprint
Monday.com
FAQs
Q: What exactly is the Model Context Protocol (MCP)?
A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.
Q: How is MCP different from OpenAI's function calling or plugins?
A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.
Q: Can I use MCP with frameworks like LangChain?
A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.
Q: Why was MCP created? What problem does it solve?
A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.
Q: Is MCP secure? What are the main risks?
A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.
Q: Who is behind MCP?
A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.



