Building a Browser Harness MCP for AI Agents
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Building a Browser Harness MCP for AI AgentsOpen example.com and print the page title."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Building a Browser Harness/MCP for AI Agents
A browser harness built with Playwright, MCP, and the GitHub Copilot SDK.
Setup
npm install
npx playwright install chromiumSet the Azure OpenAI environment variables:
export AZURE_OPENAI_ENDPOINT="https://..."
export AZURE_OPENAI_API_KEY="..."
export AZURE_OPENAI_API_VERSION="2025-04-01-preview"
export AZURE_OPENAI_DEPLOYMENT="gpt-5.4"By default, the harness launches Playwright Chromium. To attach to Chrome instead, start it with a dedicated profile and export its CDP endpoint:
google-chrome \
--remote-debugging-port=9222 \
--user-data-dir="$PWD/.agent-browser" \
--no-first-run
export BROWSER_CDP_URL="http://127.0.0.1:9222"Related MCP server: playwright-browser
Run
npm start -- "Open example.com and print the page title."Run the live tasks:
npm run eval
npm run eval -- --task amazonThe code-execution runtime is not a security boundary. Run generated code in an isolated process or VM before using this pattern with untrusted input.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to control browser automation through natural language prompts using Playwright, supporting visual element interaction, PDF generation, screenshots, and testing assertions.
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to control a web browser using Playwright, supporting navigation, interaction, and data extraction through natural language.MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to perform browser automation using Playwright, including navigation, content extraction, screenshot analysis, and custom script execution.523MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to control a browser through Playwright tools, allowing web automation tasks such as navigation, clicking, typing, and screenshots.7,623
Related MCP Connectors
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
Live browser debugging for AI assistants — DOM, console, network via MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jiin-kim109/Building-a-Browser-Harness-MCP-for-AI-Agents'
If you have feedback or need assistance with the MCP directory API, please join our Discord server