LlamaCloud

What is mcp-server-llamacloud?

mcp-server-llamacloud is a TypeScript-based MCP (Model Context Protocol) server that facilitates connecting to managed indexes on LlamaCloud. It allows users to create multiple tools, each linked to a specific LlamaCloud managed index, enabling AI-powered search and information retrieval from diverse data sources.

How to use mcp-server-llamacloud?

To use mcp-server-llamacloud, you need to add its configuration to your MCP client (e.g., Claude Desktop, Windsurf, or Cursor). This involves defining the mcpServers entry in your client's configuration file, specifying the command to run the server and providing arguments to define the LlamaCloud indexes you want to connect to. You'll also need to set your LLAMA_CLOUD_API_KEY as an environment variable.

Installation Example:

{
  "mcpServers": {
    "llamacloud": {
      "command": "npx",
      "args": [
        "-y",
        "@llamaindex/mcp-server-llamacloud",
        "--index",
        "10k-SEC-Tesla",
        "--description",
        "10k SEC documents from 2023 for Tesla",
        "--topK",
        "5",
        "--index",
        "10k-SEC-Apple",
        "--description",
        "10k SEC documents from 2023 for Apple"
      ],
      "env": {
        "LLAMA_CLOUD_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Key Features of mcp-server-llamacloud

• Tool Creation: Creates a separate tool for each LlamaCloud index you define.
• Query Parameter: Each tool provides a query parameter to search its specific index.
• Auto-generated Tool Names: Automatically generates tool names like get_information_index_name based on the index names.
• Configurable TopK: Allows specifying the topK parameter to limit the number of search results.

Use Cases of mcp-server-llamacloud

• Integrating LlamaCloud Indexes with MCP Clients: Seamlessly connect your LlamaCloud managed indexes with various MCP-compatible clients like Claude Desktop, Windsurf, or Cursor.
• AI-powered Information Retrieval: Enable advanced search and retrieval capabilities from structured and unstructured data stored in LlamaCloud indexes.
• Building Custom AI Tools: Develop specialized AI tools that leverage the power of LlamaCloud for specific domains or datasets.
• Document Analysis: Query and analyze large sets of documents, such as SEC filings, by indexing them in LlamaCloud.

FAQ about mcp-server-llamacloud

Q: What is LlamaCloud? A: LlamaCloud is a platform that provides managed indexes for storing and querying data, often used in conjunction with AI and language models for information retrieval.

Q: How do I define multiple tools? A: In the args array of your MCP config, you can define multiple tools by providing pairs of --index and --description arguments. You can also optionally specify --topK for each tool.

Q: Where can I find the MCP config for Claude Desktop? A: On MacOS, it's typically at ~/Library/Application Support/Claude/claude_desktop_config.json. On Windows, it's at %APPDATA%/Claude/claude_desktop_config.json.

Q: How can I debug the mcp-server-llamacloud? A: You can use the MCP Inspector by running npm run inspector after installing the development dependencies. The Inspector provides a URL to access debugging tools in your browser.

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:

The LLAMA_CLOUD_PROJECT_NAME environment variable is optional and defaults to Default if not set.

{
  "mcpServers": {
    "llamacloud": {
      "command": "npx",
      "args": [
        "-y",
        "@llamaindex/mcp-server-llamacloud",
        "--index",
        "10k-SEC-Tesla",
        "--description",
        "10k SEC documents from 2023 for Tesla",
        "--topK",
        "5",
        "--index",
        "10k-SEC-Apple",
        "--description",
        "10k SEC documents from 2023 for Apple"
      ],
      "env": {
        "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. You can also optionally specify --topK to limit the number of results.

For example:

--index "10k-SEC-Tesla" --description "10k SEC documents from 2023 for Tesla" --topK 5

Adds a tool for the 10k-SEC-Tesla LlamaCloud index to the MCP server. In this example, it's configured to return the top 5 results.

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.