LlamaCloud MCP Server
@run-llama
LlamaCloud MCP Server について
A MCP server connecting to managed indexes on LlamaCloud
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"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>"
}
}
}
}ツール
1generates tool names like `get_information_index_name` based on index names
概要
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
queryparameter for searching - Auto-generates tool names like
get_information_index_name - Supports optional
--topKto 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
FAQ from LlamaCloud MCP Server
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 とエージェント」の他のコンテンツ
Shell and Coding agent for Claude and other mcp clients
rusiaamanShell and coding agent on mcp clients
Gemini MCP Server
aliargunMCP server implementation for Google's Gemini API
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
Model Context Protocol Server for Home Assistant
tevonsbA MCP server for Home Assistant
MCP-LLM Bridge
patruffBridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
コメント