GibsonAI

Model Context Protocol (MCP)

GibsonAI's MCP server allows tools like Cursor, Windsurf, or Claude Desktop to create and update projects on your behalf, explain how to interact with the database and hosted APIs, and even write working code for you, all within the comfort of your own IDE. This will greatly improve the context and output of these tools while working with your Gibson project(s).

Authentication

You'll need to ensure you're logged in to the Gibson CLI before the MCP server will work.

Cursor Setup

Go to Cursor → Settings → Cursor Settings → MCP and click Add new global MCP server

Update the configuration to add the gibson server:

Windsurf Setup

Go to Windsurf → Settings → Windsurf Settings → Cascade and click Add server in the Model Context Protocol (MCP) Servers section

In the modal, click Add custom server

Update the configuration to add the gibson server:

Open the Cascade chat and, if necessary, refresh the MCP servers

Claude Desktop Setup

Go to Claude → Settings → Developer and click Edit Config

Open the claude_desktop_config.json file and update the configuration to add the gibson server:

See the Claude Desktop MCP docs for more information.

Claude Code Setup

VS Code + GitHub Copilot Setup

Create or open the .vscode/mcp.json file

Update the configuration to add the gibson server:

See the official GitHub Copilot MCP docs for more information.

Distribution

Note that this repo is for documentation purposes only. Our MCP server code lives within our CLI, which allows us to share authentication + API interaction logic with the CLI and have a single distribution. This means we're able to ship new features to you faster.