Overview

The Letta MCP Server provides a bridge between AI models and the Letta agent management system. It allows language models to create, manage, and interact with Letta agents, their memories, and associated tools in a standardized way.

Created by:

Developed by Oculair Media

Key Features

🤖

Agent Management

Create, modify, clone, and manage Letta agents

🧠

Memory Operations

Handle memory blocks and passages for agents

🔧

Tool Integration

Attach and manage tools for agents with full MCP support

📊

Enhanced Metadata

Output schemas and behavioral annotations for all tools

Available Tools

The Letta MCP server offers consolidated tools that use a discriminator pattern. You specify the desired operation within the tool arguments.

Quick Reference

Tool	Purpose	Category
`agent`	Manage Letta agents	Agent Management
`memory`	Handle memory blocks	Memory
`tool`	Manage agent tools	Tool Management

Detailed Usage

agent▶

Perform operations on Letta agents, such as creating, listing, or messaging.

// Create a new agent
use_mcp_tool({
  server_name: "letta",
  tool_name: "agent",
  arguments: {
    operation: "create_agent",
    name: "My New Agent",
    model: "openai/gpt-4"
  }
});

// Send a message to an agent
use_mcp_tool({
  server_name: "letta",
  tool_name: "agent",
  arguments: {
    operation: "message_agent",
    agent_id: "agent-123",
    message: "Hello, agent!"
  }
});

memory▶

Manage memory blocks for agents.

// Create a memory block
use_mcp_tool({
  server_name: "letta",
  tool_name: "memory",
  arguments: {
    operation: "create_memory_block",
    name: "agent_persona",
    label: "persona",
    value: "You are a helpful assistant."
  }
});

tool▶

Manage tools for agents.

// List available tools
use_mcp_tool({
  server_name: "letta",
  tool_name: "tool",
  arguments: {
    operation: "list_tools"
  }
});

Installation

{
  "mcpServers": {
    "letta": {
      "command": "npx",
      "args": [
        "-y",
        "letta-mcp-server"
      ],
      "env": {
        "LETTA_BASE_URL": "https://your-letta-instance.com/v1",
        "LETTA_PASSWORD": "your-secure-password"
      }
    }
  }
}

Sources

Cloudflare MCP Server

Interact with Cloudflare services using natural language through the Model Context Protocol.

Vectara MCP Server

Vectara MCP servers enable AI models to interact with Vectara's RAG platform, providing capabilities for fast and reliable Retrieval-Augmented Generation, semantic search, and hallucination correction.

Google Drive MCP Server

Google Drive MCP servers enable AI models to interact with Google Drive, providing capabilities for file search, content retrieval, and seamless integration with cloud storage.

Letta MCP Server