> ## 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.

# Introduction

> Connect AI agents to GiveReady using Model Context Protocol (MCP)

# MCP

MCP (Model Context Protocol) lets AI agents interact with GiveReady directly — searching nonprofits, reading profiles, and listing cause areas — all through a standardised tool-calling interface.

This means you can connect Claude, ChatGPT, Cursor, or any MCP-compatible client and discover verified nonprofits through natural language.

## How It Works

GiveReady exposes an MCP server that provides **3 tools** and **1 resource** to AI agents. The agent discovers these tools, understands their schemas, and calls them on your behalf.

```mermaid theme={null}
sequenceDiagram
    participant Agent as AI Agent
    participant MCP as GiveReady MCP Server
    participant API as GiveReady API

    Agent->>MCP: Connect via npx giveready-mcp
    MCP-->>Agent: List available tools (3 tools, 1 resource)
    Agent->>MCP: search_nonprofits({cause: "surf-therapy"})
    MCP->>API: GET /api/search?cause=surf-therapy
    API-->>MCP: Results
    MCP-->>Agent: Structured nonprofit data
```

## Installation

```bash theme={null}
npx giveready-mcp
```

Or add to your MCP client configuration:

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

## Registry

GiveReady is registered on the MCP registry as:

```
io.github.gswardman/giveready
```

**npm package:** `giveready-mcp`
