# mcp-server-llamacloud

> MCP Server

This repository hosts a TypeScript-based MCP server that connects to multiple LlamaCloud managed indexes, creating individual tools for each index based on command-line arguments. Each tool allows querying its specific index.

## Overview

- **Category:** AI
- **Language:** JavaScript
- **Stars:** 87
- **Forks:** 10
- **Owner:** run-llama
- **GitHub:** https://github.com/run-llama/mcp-server-llamacloud
- **Created:** 2024-12-04T07:45:44+00:00
- **Updated:** 2025-03-28T10:19:19+00:00
- **Source:** https://model-context-protocol.com/servers/mcp-server-llamacloud-managed-index-tools

## Setup

## Setup
To use with your MCP Client, add the following config to your MCP client config:

```json
{
  "mcpServers": {
    "llamacloud": {
      "command": "npx",
      "args": [
        "-y",
        "@llamaindex/mcp-server-llamacloud",
        "--index",
        "10k-SEC-Tesla",
        "--description",
        "10k SEC documents from 2023 for Tesla",
        "--index",
        "10k-SEC-Apple",
        "--description",
        "10k SEC documents from 2023 for Apple"
      ],
      "env": {
        "LLAMA_CLOUD_PROJECT_NAME": "<YOUR_PROJECT_NAME>",
        "LLAMA_CLOUD_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}
```

For Claude, the MCP config can be found at:

- On MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
- On Windows: `%APPDATA%/Claude/claude_desktop_config.json`

In the `args` array of the MCP config, you can define multiple tools by providing pairs of `--index` and `--description` arguments.

Install dependencies:

```bash
npm install
```

Build the server:

```bash
npm run build
```

For development with auto-rebuild:

```bash
npm run watch
```

To use the development version, replace in your MCP config `npx @llamaindex/mcp-server-llamacloud` with `node ./build/index.js`.

Debugging can be done using the MCP Inspector:

```bash
npm run inspector
```

## Tools

## Available Tools

1.  Creates a separate tool for each index you define.
2.  Each tool provides a `query` parameter to search its specific index.
3.  Auto-generates tool names like `get_information_index_name` based on index names.