What dependencies are required?
You need a Go runtime to run the server from source or a prebuilt binary, plus the Chrome browser with the companion Chrome extension installed.
@fujiron
Basic information
Chrome Extension MCP Server implemented in Go - For Model Context Protocol to interact with Chrome extensions
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"chrome-extension-mcp-go": {
"command": "docker",
"args": [
"build",
"-t",
"mcp/chromeextension-go",
"."
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Go implementation of the Model Context Protocol (MCP) server for the Chrome Extension API, enabling Claude to interact with Chrome browser extensions via a WebSocket bridge. It provides a set of tools for performing browser operations such as tab management, DOM manipulation, CSS injection, and screenshot capture.
Install the Chrome extension by either building the Docker container and extracting the extension package, or manually loading the extension directory from extension/. Run the Go server with go run main.go or the compiled binary. Then configure Claude’s MCP server settings in claude_desktop_config.json by specifying the server binary and the CHROME_EXTENSION_ID environment variable.
You need a Go runtime to run the server from source or a prebuilt binary, plus the Chrome browser with the companion Chrome extension installed.
Add a MCP server entry to your `claude_desktop_config.json` with the command pointing to the binary and set the `CHROME_EXTENSION_ID` environment variable to the installed extension’s ID.
The server uses a WebSocket to communicate with the Chrome extension, and implements the Model Context Protocol (MCP) to expose tools to Claude.
You can either build the Docker image and extract the extension directory, or manually navigate to the `extension/` folder and load it as an unpacked extension in Chrome’s developer mode at `chrome://extensions/`.
Codebase health as MCP tools: dead code, circular dependencies, coupling, architectural drift.

OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
Comments