MCP server for providing web context to LLMs using Cloudflare Browser Rendering
Cloudflare browser rendering mcp mcp server lets Claude, Cursor and other MCP clients work with Cloudflare Browser Rendering MCP directly. MCP server for providing web context to LLMs using Cloudflare Browser Rendering.
This MCP (Model Context Protocol) server provides tools for fetching and processing web content using Cloudflare Browser Rendering for use as context in LLMs. It's designed to work with both Claude and Cline client environments.
Once connected, the assistant can call these 8 tools directly:
fetch_page — The fetch_page tool exposed by this serversearch_documentation — Searches Cloudflare documentation and returns relevant contentextract_structured_content — Extracts structured content from a web page using CSS selectorssummarize_content — The summarize_content tool exposed by this servertake_screenshot — The take_screenshot tool exposed by this serverLogging — The MCP server uses comprehensive logging with the following prefixes:Building — The Building tool exposed by this serverTesting — The project includes a comprehensive test script that verifies all MCP tools are working correctly:The server is distributed via npm as @smithery/cli, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
The server reads one environment variable: BROWSER_RENDERING_API. Keep credentials in your client's env block or a secrets manager rather than committing them.
puppeteer-worker.js fileCloud and DevOps servers put infrastructure on speaking terms with your assistant, so "why is this broken?" is answered from real state rather than a generic checklist. Cloudflare Browser Rendering MCP sits in that group, and the shape of its toolset — fetch_page, search_documentation, extract_structured_content among others — tells you what it is really for. Worth comparing against the other cloud devops servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| fetch_page | The fetch_page tool exposed by this server. |
| search_documentation | Searches Cloudflare documentation and returns relevant content. |
| extract_structured_content | Extracts structured content from a web page using CSS selectors. |
| summarize_content | The summarize_content tool exposed by this server. |
| take_screenshot | The take_screenshot tool exposed by this server. |
| Logging | The MCP server uses comprehensive logging with the following prefixes: |
| Building | The Building tool exposed by this server. |
| Testing | The project includes a comprehensive test script that verifies all MCP tools are working correctly: |
{
"mcpServers": {
"cloudflare-browser-rendering": {
"command": "npx",
"args": ["-y", "@smithery/cli"],
"env": {
"BROWSER_RENDERING_API": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
puppeteer-worker.js file| Variable | Description | Required |
|---|---|---|
| BROWSER_RENDERING_API | Configuration value read at startup. | Optional |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.