LlamaCloud MCP Server

@run-llama

代码仓库

基本信息

分类

AI 与智能体

许可证

MIT

传输方式

stdio

作者

run-llama

关于 LlamaCloud MCP Server

A MCP server connecting to managed indexes on LlamaCloud

#llamacloud#mcp-server#managed-index

LlamaCloud MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "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>"
      }
    }
  }
}

LlamaCloud MCP Server 工具

generates tool names like `get_information_index_name` based on index names

概览

What is LlamaCloud MCP Server?

LlamaCloud MCP Server is a TypeScript-based MCP server that connects to multiple managed indexes on LlamaCloud. It creates separate MCP tools for each index, allowing users to query their LlamaCloud documents through an MCP client.

How to use LlamaCloud MCP Server?

Configure the server in your MCP client (e.g., Claude Desktop, Windsurf, or Cursor) by adding an entry with command npx -y @llamaindex/mcp-server-llamacloud and passing --index, --description, and optionally --topK arguments for each index. Set the LLAMA_CLOUD_API_KEY environment variable to your API key.

Key features of LlamaCloud MCP Server

Creates a separate tool for each defined index
Each tool provides a query parameter for searching
Auto-generates tool names like get_information_index_name
Supports optional --topK to limit results per tool

Use cases of LlamaCloud MCP Server

Querying 10k SEC documents for multiple companies from a single server
Searching indexed knowledge bases through an MCP client interface
Managing and querying multiple LlamaCloud projects within one agent

常见问题

How do I configure the server for my MCP client?

Add a JSON entry to your MCP client config with command `npx -y @llamaindex/mcp-server-llamacloud`, provide `--index` and `--description` pairs, and set `LLAMA_CLOUD_API_KEY` in the `env` block.

Where can I find my MCP client configuration file?

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

How do I define multiple indexes (tools)?

Repeat the `--index` and `--description` arguments in the `args` array. Each pair creates a new tool. Optionally add `--topK` after a pair to limit its results.

What environment variables are required?

`LLAMA_CLOUD_API_KEY` is required. `LLAMA_CLOUD_PROJECT_NAME` is optional and defaults to `Default` if not set.

How can I debug the server?

Use the MCP Inspector by running `npm run inspector` from the project directory. It provides a URL with debugging tools for stdio-based MCP servers.

AI 与智能体分类下的更多 MCP 服务器

localscreenshot - website screenshot mcp for ai agents

localscreenshot is a Website screenshot MCP server and API available at https://localscreenshot.com/api. Localscreenshot screenshot api turns any public web page into an image or a PDF. Take the capture from one of 227 c

OpenZiti MCP Gateway

openziti

NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure

Agentery

ntlgnc

Free MCP for live and historical pricing for 13,000+ agents and MCPs. Never knowingly pay too much... or charge too little. Know the going rate. https://agentery.com.

kosa8

kosa8ai

Secure infrastructure for AI agents: sealed microVM sandboxes you can checkpoint, rewind and fork.

Agent Traffic Lab

ATL doesn’t just help agents find tools — it gets the job done. It finds and chooses the right AI provider, tool, or MCP server, executes the task, and switches to a fallback when a provider fails. It can optimize for lo