# Playwright MCP

Model Context Protocol server that exposes Playwright browser automation capabilities to AI agents for web interaction and testing.

## Agent Decision Summary
- Risk level: elevated
- Source confidence: high
- Recommended workflows: Browser automation, Coding agent workflow, Connector or protocol layer
- Permission surface: browser, shell/files, memory, external services
- Agent JSON: https://www.openagent.bot/plugins/playwright-mcp.agent.json

## Summary
Playwright MCP is an open-source Model Context Protocol server from Microsoft that provides AI agents with browser automation capabilities through standardized MCP tools. It enables agents to navigate pages, click elements, fill forms, take screenshots, and run Playwright tests.


## Guide

### FAQ
- What is Playwright MCP?
  - Playwright MCP is an open-source Model Context Protocol server from Microsoft that exposes Playwright browser automation capabilities to AI agents, enabling web navigation and interaction through standardized MCP tools.
- Is Playwright MCP free?
  - Yes, Playwright MCP is open-source under the Apache-2.0 license and maintained by Microsoft. It can be self-hosted as a Node.js process.
- How does Playwright MCP differ from browser-use?
  - Playwright MCP provides browser control through the MCP protocol, making it compatible with any MCP-enabled agent host. browser-use is a Python framework designed specifically for LLM-native browser control with natural language goal setting.
- Which agents support Playwright MCP?
  - Any MCP-compatible agent host can use Playwright MCP, including Claude Desktop, OpenClaw, Cline, Continue.dev, and other MCP-enabled tools.
- Can Playwright MCP take screenshots?
  - Yes. Playwright MCP supports taking screenshots of web pages, filling forms, clicking elements, extracting page content, and running Playwright test scripts through its MCP tool interface.
## What It Does
Playwright MCP is a plugin in the plugins category. Playwright MCP is an open-source Model Context Protocol server from Microsoft that provides AI agents with browser automation capabilities through standardized MCP tools. It enables agents to navigate pages, click elements, fill forms, take screenshots, and run Playwright tests.

## How To Evaluate
Evaluate Playwright MCP by starting from the official sources, checking its repo, docs, mcp interface surface, and running one narrow workflow before expanding scope.

## Why It Matters
Agents that need to interact with web pages currently require custom scraping or API integrations. Playwright MCP gives agents direct browser control through an MCP interface, enabling visual web interaction without custom code.


## Best For
- Developers building browser-based AI agents
- Teams using MCP-compatible agent hosts for web automation
- Builders who need visual web interaction in agent workflows

## Not For
- Teams that need only deterministic testing without AI
- Workflows already using browser-use for LLM-native browser control

## Fit Matrix
- Browser automation: strong. Playwright MCP has multiple signals for browser automation, including matching tags, capabilities, category, or positioning. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Coding agent workflow: strong. Playwright MCP has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Connector or protocol layer: strong. Playwright MCP has multiple signals for connector or protocol layer, including matching tags, capabilities, category, or positioning. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Evaluation and observability: partial. Playwright MCP has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Local or private AI stack: partial. Playwright MCP has at least one signal for local or private ai stack, but should be checked against a real task before adoption. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
- Memory or RAG workflow: partial. Playwright MCP has at least one signal for memory or rag workflow, but should be checked against a real task before adoption. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data.

## Evidence
- verified: Playwright MCP is listed as open source. Source: License metadata: Apache-2.0
- verified: Playwright MCP has a recorded GitHub repository: microsoft/playwright-mcp. Source: Resource facts and GitHub source link.
- inferred: Playwright MCP supports these recorded deployment modes: self hosted. Source: OpenAgent decision signal metadata.
- inferred: Playwright MCP is tagged with plugin, mcp, browser automation, protocol capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/microsoft/playwright-mcp
- Read setup docs: https://github.com/microsoft/playwright-mcp?tab=readme-ov-file#readme

## Facts
- Category: plugins
- Resource type: plugin
- Open source: yes
- License: Apache-2.0
- Last verified: 2026-06-24
- GitHub repo: microsoft/playwright-mcp
- GitHub stars: 18000

## Capabilities
- plugin
- mcp
- browser-automation
- protocol

## Structured Use Case Tags
- browser-agent
- developer-workflow
- self-hosted-ai

## Links
- GitHub: https://github.com/microsoft/playwright-mcp
- Documentation: https://github.com/microsoft/playwright-mcp?tab=readme-ov-file#readme

## Structured Outputs
- JSON: https://www.openagent.bot/plugins/playwright-mcp.json
- Markdown: https://www.openagent.bot/plugins/playwright-mcp.md
- Agent JSON: https://www.openagent.bot/plugins/playwright-mcp.agent.json
- Canonical: https://www.openagent.bot/plugins/playwright-mcp