What is LlamaCloud

The LlamaCloud MCP Server is a TypeScript-based server that connects to multiple managed indexes on LlamaCloud, allowing users to create tools for querying specific indexes. Each tool is generated based on command-line arguments, enabling tailored searches for different datasets.

Use cases

This server is useful for developers and data researchers who want to easily interact with and retrieve information from various managed indexes on LlamaCloud. It allows for querying specific datasets, such as SEC documents for different companies, thereby facilitating data-driven decision-making and analysis.

How to use

To use the LlamaCloud MCP Server, you need to configure your MCP client (like Claude Desktop) by adding a command in the client’s configuration file. This involves specifying the index and description for each tool you wish to create, along with necessary environment variables for authentication.

Key features

The key features of the LlamaCloud MCP Server include the ability to create individual tools for each specified index, auto-generating meaningful tool names, and providing a query parameter for interacting with the specific indexes. Its design allows for flexibility and ease of use in managing multiple data sources.

Where to use

The LlamaCloud MCP Server is primarily used within MCP clients that support integration with external tools. It is ideal for environments where users need to manage and query multiple indexes effortlessly, such as in data analysis platforms, research applications, or any workflow requiring access to diverse datasets.

LlamaCloud MCP Server

A MCP server connecting to multiple managed indexes on LlamaCloud

This is a TypeScript-based MCP server that creates multiple tools, each connected to a specific managed index on LlamaCloud. Each tool is defined through command-line arguments.

Features

Tools

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

Installation

To use with your MCP Client (e.g. Claude Desktop, Windsurf or Cursor), add the following config to your MCP client config:

{
  "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

Tool Definition Format

In the args array of the MCP config, you can define multiple tools by providing pairs of --index and --description arguments. Each pair defines a new tool.

For example:

--index "10k-SEC-Tesla" --description "10k SEC documents from 2023 for Tesla"

Adds a tool for the 10k-SEC-Tesla LlamaCloud index to the MCP server.

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

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

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.