Playwright MCP
An MCP server that provides structured control of a Playwright browser for QA, scraping, diagnostics, and reproducible browser workflows.
README
Playwright MCP
An MCP server that gives compatible clients structured control of a real Playwright browser for QA, scraping diagnostics, accessibility-minded inspection, and reproducible browser workflows.
Architecture
Transport entrypoints are thin:
src/index.tsstarts MCP over stdio.src/http.tsstarts MCP over Streamable HTTP.src/server.tsbuilds oneMcpServerand registers all tools.
Core services own browser state:
BrowserManagerserializes tool execution, launches browsers lazily, and manages contexts/pages.TelemetryStorecaptures console messages, page errors, failed requests, and recent network events.- Tool modules register focused actions and depend only on the public browser/session APIs.
Tool groups:
- Browser/context/page lifecycle
- Navigation and waiting
- Interaction
- Inspection and screenshots
- Assertions
- Diagnostics, tracing, and storage
Install
npm install
npm run install-browsers
npm run build
Run
npm start
HTTP transport:
npm run start:http
Default HTTP endpoint: http://127.0.0.1:8931/mcp.
Production Controls
Configuration is environment-driven:
PLAYWRIGHT_MCP_HTTP_TOKEN: requireAuthorization: Bearer <token>for HTTP mode.PLAYWRIGHT_MCP_HTTP_ALLOWED_ORIGINS: comma-separated CORS allowlist.PLAYWRIGHT_MCP_ALLOWED_ORIGINS: comma-separated browser navigation allowlist.PLAYWRIGHT_MCP_BLOCKED_ORIGINS: comma-separated browser navigation blocklist.PLAYWRIGHT_MCP_ALLOW_EVALUATE: enable the dangerousevaluatetool. Default:false.PLAYWRIGHT_MCP_ALLOW_DOWNLOADS: enable download tools and accepting downloads. Default:false.PLAYWRIGHT_MCP_ALLOW_UPLOADS: enable upload tools. Default:false.PLAYWRIGHT_MCP_ARTIFACT_DIR: screenshots, traces, PDFs, downloads, and storage state directory. Default:./artifacts.PLAYWRIGHT_MCP_MAX_CONTEXTS: browser context cap. Default:8.PLAYWRIGHT_MCP_MAX_PAGES: page cap. Default:32.PLAYWRIGHT_MCP_DEFAULT_TIMEOUT_MS: default Playwright timeout. Default:30000.PLAYWRIGHT_MCP_LOG_LEVEL:debug,info,warn, orerror.
HTTP mode should use PLAYWRIGHT_MCP_HTTP_TOKEN before binding to anything other than localhost.
MCP client config
Examples are available in examples/:
claude_config.jsoncursor_mcp.jsoncodex_config.tomlcline_mcp_settings.jsonopencode_config.json
Development
npm run check
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.