pydoll
PyDoll MCP Server is a Model Context Protocol (MCP) server built on PyDoll, a next-generation browser automation library. It enables AI assistants like Claude to naturally control web browsers and perform complex web automation tasks.
claude mcp add --transport stdio jinsongroh-pydoll-mcp python -m pydoll_mcp
How to use
PyDoll MCP Server (pydoll) exposes PyDoll-based browser automation capabilities via MCP, enabling remote control of browser actions without a traditional WebDriver session. The server leverages PyDoll's native API for tab management, element finding, searches, and browser interactions, along with enhancements for Windows compatibility and robust error handling. Tools mentioned in the server are designed to provide intelligent search automation, resilient element discovery, and reliable tab lifecycle operations, with improved asynchronous patterns for responsiveness. To use it, run the MCP server and connect through an MCP client to issue commands like opening tabs, navigating pages, finding elements with selectors or attributes, performing searches, and executing scripted actions within browser tabs. Expect improved stability when dealing with cross-platform Windows environments and captchas, as the server incorporates PyDoll integration and fallback strategies for common automation scenarios.
How to install
Prerequisites:
- Python 3.8+ (recommended)
- pip (bundled with Python)
Step 1: Create a virtual environment (optional but recommended)
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
Step 2: Install the MCP server package from PyPI
pip install pydoll-mcp
Step 3: Verify installation
python -m pydoll_mcp --help
Step 4: Run the MCP server (example)
python -m pydoll_mcp
Step 5: (Optional) Run with a specific configuration file or environment variables as needed for your deployment
export PYDOLL_MCP_CONFIG=/path/to/config.json
python -m pydoll_mcp
Additional notes
Notes and tips:
- The server is Python-based and uses the pydoll-mcp package. If you upgrade, pin to the desired version (e.g., pydoll-mcp==1.5.16).
- If you encounter Windows-specific issues, ensure you have compatible Chrome/Chromium binaries and PyDoll runtime libraries installed.
- MCP environment variables can customize logging, timeouts, and API endpoints; refer to the PyDoll MCP docs for available options.
- For troubleshooting, enable verbose logging to capture detailed browser operations and tab lifecycle events.
Related MCP Servers
MCP-Bridge
A middleware to provide an openAI compatible endpoint that can call MCP tools
mcp-pinecone
Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG
pfsense
pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in complian
mcp-kubernetes
A Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes, translating natural language requests into Kubernetes operations and returning the results in a format the AI tools can understand.
mcp -templates
A flexible platform that provides Docker & Kubernetes backends, a lightweight CLI (mcpt), and client utilities for seamless MCP integration. Spin up servers from templates, route requests through a single endpoint with load balancing, and support both deployed (HTTP) and local (stdio) transports — all with sensible defaults and YAML-based configs.
davinci -professional
An enterprise-grade MCP server that exposes the full functionality of DaVinci Resolve and DaVinci Resolve Studio (through version 20) to either Claude Desktop or Cursor MCP clients. Fully configured and tested as a Claude Desktop Extension making installation as easy as clicking a button. Supports both Windows and Macintosh.
