LlamaCloud MCP Server

LlamaCloud MCP Server

Connect multiple LlamaCloud indexes as tools for your MCP client.

82
Stars
17
Forks
82
Watchers
2
Issues
LlamaCloud MCP Server is a TypeScript-based implementation of a Model Context Protocol server that allows users to connect multiple managed indexes from LlamaCloud as separate tools in MCP-compatible clients. Each tool is defined via command-line parameters, enabling flexible and dynamic access to different document indexes. The server automatically generates tool interfaces, each capable of querying its respective LlamaCloud index, with customizable parameters such as index name, description, and result limits. Designed for seamless integration, it works with clients like Claude Desktop, Windsurf, and Cursor.

Key Features

Supports multiple managed LlamaCloud indexes as tools
Auto-generates tool names based on indexes
Customizable tool descriptions and query parameters
Configurable number of results (topK)
Integration with popular MCP clients (Claude Desktop, Windsurf, Cursor)
Command-line based tool configuration
Stdio-based MCP communication
Development scripts for building and debugging
Optional project naming via environment variables
Includes MCP Inspector integration for debugging

Use Cases

Connecting multiple document indexes for AI-driven search
Providing standardized access to LlamaCloud indexes from context-aware clients
Configuring custom tools for different data sets in enterprise search
Enhancing context retrieval workflows in conversational AI applications
Facilitating research by enabling targeted queries across distinct document collections
Supporting development and testing of MCP integrations
Tailoring knowledge bases for different user groups or clients
Debugging and inspecting MCP server interactions
Integrating document search capabilities into AI tools
Automated tool provisioning and scaling for managed indexes

README

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.

json
{
  "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:

bash
--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:

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

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

bash
npm run inspector

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

Star History

Star History Chart

Repository Owner

run-llama
run-llama

Organization

Repository Details

Language JavaScript
Default Branch main
Size 249 KB
Contributors 4
License MIT License
MCP Verified Nov 12, 2025

Programming Languages

JavaScript
100%

Tags

Topics

aitool llamaindex mcp mcp-server

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • @dealx/mcp-server

    @dealx/mcp-server

    MCP server enabling LLMs to search and interact with the DealX platform.

    Implements the Model Context Protocol, providing a standardized interface for large language models to interact with the DealX platform. Supports searching for ads through structured prompts and is designed for easy integration with tools like Claude and VS Code extensions. Flexible configuration options are available for environment variables, logging, and deployment. Extensible architecture supports future feature additions beyond ad search.

    • 0
    • MCP
    • DealExpress/mcp-server
  • MyMCP Server (All-in-One Model Context Protocol)

    MyMCP Server (All-in-One Model Context Protocol)

    Powerful and extensible Model Context Protocol server with developer and productivity integrations.

    MyMCP Server is a robust Model Context Protocol (MCP) server implementation that integrates with services like GitLab, Jira, Confluence, YouTube, Google Workspace, and more. It provides AI-powered search, contextual tool execution, and workflow automation for development and productivity tasks. The system supports extensive configuration and enables selective activation of grouped toolsets for various environments. Installation and deployment are streamlined, with both automated and manual setup options available.

    • 93
    • MCP
    • nguyenvanduocit/all-in-one-model-context-protocol
  • Ragie Model Context Protocol Server

    Ragie Model Context Protocol Server

    Seamless knowledge base retrieval via Model Context Protocol for enhanced AI context.

    Ragie Model Context Protocol Server enables AI models to access and retrieve information from a Ragie-managed knowledge base using the standardized Model Context Protocol (MCP). It provides a retrieve tool with customizable query options and supports integration with tools like Cursor and Claude Desktop. Users can configure API keys, specify partitions, and override tool descriptions. Designed for rapid setup via npx and flexible for project-specific or global usage.

    • 81
    • MCP
    • ragieai/ragie-mcp-server
  • YAMCP

    YAMCP

    Unified management and orchestration of Model Context Protocol servers via a local gateway workspace.

    YAMCP is a command-line tool that enables organizing and managing multiple MCP (Model Context Protocol) servers as unified workspaces. It allows users to connect to various local or remote MCP servers, group them by functionality or application, and expose them as a single MCP server gateway for AI applications. The tool simplifies monitoring and debugging by centralizing server communication logs and provides workspace management and runtime control. YAMCP facilitates seamless integration with AI applications by providing a consolidated configuration and context management interface.

    • 57
    • MCP
    • hamidra/yamcp
  • mcp-get

    mcp-get

    A command-line tool for discovering, installing, and managing Model Context Protocol servers.

    mcp-get is a CLI tool designed to help users discover, install, and manage Model Context Protocol (MCP) servers. It enables seamless integration of Large Language Models (LLMs) with various external data sources and tools by utilizing a standardized protocol. The tool provides access to a curated registry of MCP servers and supports installation and management across multiple programming languages and environments. Although now archived, mcp-get simplifies environment variable management, package versioning, and server updates to enhance the LLM ecosystem.

    • 497
    • MCP
    • michaellatman/mcp-get
  • searchcraft-mcp-server

    searchcraft-mcp-server

    An MCP Server for managing Searchcraft clusters and powering AI-driven search administration.

    searchcraft-mcp-server is a TypeScript/Node.js server that implements the Model Context Protocol (MCP) for Searchcraft clusters. It provides a suite of programmable tools for managing indexes, documents, federations, access keys, and analytics using plain English prompts via AI model clients. The server enables seamless interaction between AI interfaces like Claude Desktop and Searchcraft's administrative functions by exposing these operations as protocol-driven actions.

    • 6
    • MCP
    • searchcraft-inc/searchcraft-mcp-server
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results