Lightpanda Go MCP server
A Go-based MCP server for interacting with the Lightpanda Browser using the Chrome DevTools Protocol (CDP).
Lightpanda Go MCP server
:warning: This project was a first experiment to expose an MCP for Lightpanda Browser. But now, the browser embed an MCP server natively. More details in the native MCP blog post.
gomcp is an MCP server written in
Go.
It exposes tools to interact with Lightpanda Browser via CDP protocol.
flowchart LR;
A[CDP Client]-->|SSE or stdio|gomcp;
gomcp-->|CDP|B[Lightpanda browser];
Installation
Requirements
gomcp requires you to have already installed Lightpanda
Browser.
Build from source
You need to install Go to build from source.
Once you have cloned the repository, build the binary with go build.
Usage
By default, gocmp starts a local instance of Lightpanda browser.
On the first run, you need to download the binary with the command:
$ gomcp download
The browser is stored in the user config directory.
$XDG_CONFIG_HOME/lightpanda-gomcp or HOME/.config/lightpanda-gomcp on
Linux, $HOME/Library/Application Support/lightpanda-gomcp on Macosx.
You can remove the downloaded binary with gomcp cleanup command.
You can connect on a remote browser with the option --cdp.
$ gomcp -cdp ws://127.0.0.1:9222 stdio
Configure Claude Desktop
You can configure gomcp as a source for your Claude
Desktop.
Claude Desktop uses the stdio transport to connect to an MCP server.
Edit the claude_desktop_config.json configuration file and add gomcp as the mcp
server and restart Claude Desktop.
{
"mcpServers": {
"lightpanda": {
"command": "/path/to/gomcp",
"args": ["stdio"]
}
}
}
The model context protocol website gives a way to find claude_desktop_config.json file.
Standard input/output (stdio)
You can start gomcp as a
stdio.
$ ./gomcp stdio
Server-Sent Events (SSE)
You can start gomcp as a
SSE.
By default, the server listens to the HTTP connection at 127.0.0.1:8081.
$ ./gomcp sse
2025/05/06 14:37:13 INFO server listening addr=127.0.0.1:8081
Thanks
gomcp is built thanks of open source projects, in particular:
相关服务器
Bright Data
赞助Discover, extract, and interact with the web - one interface powering automated access across the public internet.
DeepResearch MCP
A powerful research assistant for conducting iterative web searches, analysis, and report generation.
Crawl4AI RAG
Integrates web crawling and Retrieval-Augmented Generation (RAG) into AI agents and coding assistants.
Weibo
Scrape Weibo user information, feeds, and perform searches.
Puppeteer
A server for browser automation using Puppeteer, enabling web scraping, screenshots, and JavaScript execution.
Scrapeless
Integrate real-time Scrapeless Google SERP(Google Search, Google Flight, Google Map, Google Jobs....) results into your LLM applications. This server enables dynamic context retrieval for AI workflows, chatbots, and research tools.
Rapidproxy
Over 70M+ premium IPs via Rapidproxy - Enjoy easy data extraction, avoiding CAPTCHAs, IP blocks with 220+ locations targeting, non-expiring traffic.
Playwright Server
A server for browser automation using the Playwright library.
ScrapeGraph AI
AI-powered web scraping using the ScrapeGraph AI API. Requires an API key.
Query Table
A financial web table crawler using Playwright that queries data from multiple websites with fallback switching.
Scrapling Fetch MCP
Fetches HTML and markdown from websites with anti-automation measures using Scrapling.