MCP Servers

Connect external tools and data sources using the Model Context Protocol. Give your AI access to databases, APIs, and more.

What is MCP?

The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and data sources. With MCP, your AI can:

Query databases directly
Interact with APIs (GitHub, Stripe, etc.)
Access private documentation
Use custom tools you build

Configuring MCP

Add MCP servers in your workspace settings. Create or edit .grid/mcp.json:

{
  "mcpServers": {
    "supabase": {
      "command": "npx",
      "args": ["@supabase/mcp-server"],
      "env": {
        "SUPABASE_URL": "your-url",
        "SUPABASE_KEY": "your-key"
      }
    },
    "github": {
      "command": "npx",
      "args": ["@github/mcp-server"],
      "env": {
        "GITHUB_TOKEN": "ghp_..."
      }
    }
  }
}

Popular MCP Servers

Supabase

Database queries, auth management

GitHub

Issues, PRs, code search

Stripe

Payments, subscriptions

PostgreSQL

Direct database access

Filesystem

Extended file operations

Web Search

Real-time web search

Dashboard MCP vs IDE MCP

You can configure MCP servers both in the IDE (per-workspace) and in the Dashboard (organization-wide). Dashboard servers are shared across your team.