Playwright MCP
Enables browser automation and web scraping by exposing Playwright tools through an HTTP-based MCP server. Users can navigate pages, interact with web elements, capture screenshots, and extract structured content using a persistent Chromium instance.
README
Playwright MCP
FastMCP server with Playwright for browser automation and web scraping. Exposes tools over HTTP for use with MCP clients (e.g. GPT-based agents).
Features
- HTTP transport – Server runs as an HTTP service; clients connect via URL.
- Long-lived browser – One Chromium instance started at server startup (Option A).
- Structured logging – Structlog with configurable level and JSON output.
- Modular layout – Config, logging, browser, tools, and server are separate; state is injected via lifespan context.
Tools
| Tool | Description |
|---|---|
browser_navigate |
Navigate to a URL |
browser_snapshot |
Get HTML/text snapshot of the current page |
browser_tabs |
List open tabs (pages) |
browser_click |
Click an element by CSS selector |
browser_type |
Type text into an element |
browser_fill_form |
Fill multiple form fields (selector → value map) |
browser_scrape |
Extract content (text, HTML, or links) from current page or URL |
browser_screenshot |
Take a PNG screenshot (base64) of page or element |
Requirements
- Python 3.10+
- Playwright browsers (install after
pip install)
Setup
# From project root
pip install -e .
python -m playwright install chromium
Optional: copy .env.example to .env and adjust MCP_HOST, MCP_PORT, HEADLESS, LOG_LEVEL, LOG_JSON.
Run
# After pip install -e .
playwright-mcp
# Or
python -m playwright_mcp.main
Server listens at http://127.0.0.1:8000 by default. MCP endpoint is typically at http://127.0.0.1:8000/mcp (see FastMCP HTTP deployment docs).
Project layout
src/playwright_mcp/
├── main.py # Entrypoint
├── config/ # Env-based settings
├── logging_/ # Structlog setup and get_logger
├── browser/ # Lifecycle and BrowserState
├── tools/ # Navigation, interaction, scraping, screenshot
└── server/ # FastMCP app and dependency registration
Configuration
| Env var | Default | Description |
|---|---|---|
MCP_HOST |
127.0.0.1 |
HTTP bind host |
MCP_PORT |
8000 |
HTTP bind port |
HEADLESS |
true |
Run browser headless |
LOG_LEVEL |
INFO |
Log level (DEBUG, INFO, WARNING, ERROR) |
LOG_JSON |
false |
Output logs as JSON |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.