> ## Documentation Index
> Fetch the complete documentation index at: https://docs.giveready.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Connecting

> Connect GiveReady MCP to your AI agent or client

# Connecting

## Claude Desktop

Add to your Claude Desktop MCP configuration (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):

```json theme={null}
{
  "mcpServers": {
    "giveready": {
      "command": "npx",
      "args": ["giveready-mcp"]
    }
  }
}
```

Restart Claude Desktop. You can now ask Claude about nonprofits, causes, and donations naturally.

## Cursor

Add to your Cursor MCP settings (`.cursor/mcp.json`):

```json theme={null}
{
  "mcpServers": {
    "giveready": {
      "command": "npx",
      "args": ["giveready-mcp"]
    }
  }
}
```

## ChatGPT (via MCP bridge)

If you're using an MCP-to-ChatGPT bridge, add GiveReady as a server:

```json theme={null}
{
  "command": "npx",
  "args": ["giveready-mcp"]
}
```

## n8n / LangChain / CrewAI

For agent framework integrations, use the REST API directly:

```python theme={null}
import requests

# Search nonprofits
response = requests.get("https://giveready.org/api/search", params={
    "cause": "surf-therapy",
    "country": "United Kingdom"
})
nonprofits = response.json()["results"]
```

## Verifying the Connection

Once connected, test with a simple query:

```
"How many nonprofits are on GiveReady?"
"Find youth charities that use surf therapy"
"Tell me about Bridges for Music"
```

The agent should use the `search_nonprofits` or `get_nonprofit` tools and return structured data from the GiveReady directory.