Llamacloud

MCP server that connects to a managed LlamaCloud index and exposes knowledge-base querying via MCP clients.

typescript

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-run-llama_mcp-server-llamacloud": {
      "command": "node",
      "args": [
        "/path/to/llamacloud/build/index.js"
      ],
      "env": {
        "LLAMA_CLOUD_API_KEY": "<YOUR_API_KEY>",
        "LLAMA_CLOUD_INDEX_NAME": "<YOUR_INDEX_NAME>",
        "LLAMA_CLOUD_PROJECT_NAME": "<YOUR_PROJECT_NAME>"
      }
    }
  }
}

You are running a MCP server that connects to a managed LlamaCloud index. This server lets you query your knowledge base and have it answered through the MCP interface, enabling streamlined access to your index data from MCP clients.

How to use

You will run the MCP server locally and connect your MCP client to it. Once connected, you can perform knowledge-base queries against your LlamaCloud index and receive answers generated from your managed index. Use the server as a backend for querying information and for actions that require access to your knowledge base, all through the MCP client’s standard workflow.

How to install

Prerequisites: ensure you have Node.js installed on your system.

Install dependencies.

npm install

Build the server.

npm run build

For development with auto-rebuild, run the watcher.

npm run watch

Additional sections

Configuration to use with Claude Desktop is provided below. This config shows how to register the LlamaCloud MCP server with the desktop application and which environment variables must be set to connect to your specific LlamaCloud index and project.

{
  "mcpServers": {
    "llamacloud": {
      "command": "node",
      "args": [
        "/path/to/llamacloud/build/index.js",
      ],
      "env": {
        "LLAMA_CLOUD_INDEX_NAME": "<YOUR_INDEX_NAME>",
        "LLAMA_CLOUD_PROJECT_NAME": "<YOUR_PROJECT_NAME>",
        "LLAMA_CLOUD_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Debugging

MCP servers communicate over standard input/output, which can be challenging to debug. Use the MCP Inspector to access debugging tools in your browser.

npm run inspector

Available tools

get_information

Query the knowledge base to retrieve information in response to user questions.

Built by

VeilStrat

AI signals for GTM teams