MemGPT MCP Server

MemGPT MCP Server

By Vic563 GitHub

A Model Context Protocol (MCP) server that provides persistent memory and multi-model LLM support.

memgpt mcp-server
Overview

what is MemGPT MCP Server?

MemGPT MCP Server is a TypeScript-based Model Context Protocol (MCP) server that provides persistent memory and multi-model support for large language models (LLMs). It allows users to chat with various LLM providers while maintaining conversation history.

how to use MemGPT MCP Server?

To use MemGPT MCP Server, install the necessary dependencies, build the server, and configure it with your LLM provider API keys. You can then interact with the server through its tools to send messages, retrieve memory, or switch providers.

key features of MemGPT MCP Server?

  • Supports multiple LLM providers (OpenAI, Anthropic, OpenRouter, Ollama)
  • Tools for sending messages, retrieving, and clearing conversation history
  • Ability to switch between different models and providers
  • Unlimited memory retrieval option

use cases of MemGPT MCP Server?

  1. Engaging in conversations with various LLMs while keeping track of context.
  2. Utilizing different models for specific tasks like customer support or content generation.
  3. Debugging and inspecting LLM interactions using the MCP Inspector.

FAQ from MemGPT MCP Server?

  • Can I use multiple LLM providers with MemGPT?

Yes! MemGPT supports multiple providers including OpenAI and Anthropic.

  • How do I retrieve my conversation history?

You can use the get_memory tool to retrieve your conversation history, with options for limiting the number of memories.

  • Is there a way to clear my conversation history?

Yes! You can use the clear_memory tool to remove all stored memories.

Content

MemGPT MCP Server

A TypeScript-based MCP server that implements a memory system for LLMs. It provides tools for chatting with different LLM providers while maintaining conversation history.

Features

Tools

  • chat - Send a message to the current LLM provider

    • Takes a message parameter
    • Supports multiple providers (OpenAI, Anthropic, OpenRouter, Ollama)
  • get_memory - Retrieve conversation history

    • Optional limit parameter to specify number of memories to retrieve
    • Pass limit: null for unlimited memory retrieval
    • Returns memories in chronological order with timestamps
  • clear_memory - Clear conversation history

    • Removes all stored memories
  • use_provider - Switch between different LLM providers

    • Supports OpenAI, Anthropic, OpenRouter, and Ollama
    • Persists provider selection
  • use_model - Switch to a different model for the current provider

    • Supports provider-specific models:
      • Anthropic Claude Models:
        • Claude 3 Series:
          • claude-3-haiku: Fastest response times, ideal for tasks like customer support and content moderation
          • claude-3-sonnet: Balanced performance for general-purpose use
          • claude-3-opus: Advanced model for complex reasoning and high-performance tasks
        • Claude 3.5 Series:
          • claude-3.5-haiku: Enhanced speed and cost-effectiveness
          • claude-3.5-sonnet: Superior performance with computer interaction capabilities
      • OpenAI: 'gpt-4o', 'gpt-4o-mini', 'gpt-4-turbo'
      • OpenRouter: Any model in 'provider/model' format (e.g., 'openai/gpt-4', 'anthropic/claude-2')
      • Ollama: Any locally available model (e.g., 'llama2', 'codellama')
    • Persists model selection

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop, add the server config:

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

{
  "mcpServers": {
    "letta-memgpt": {
      "command": "/path/to/memgpt-server/build/index.js",
      "env": {
        "OPENAI_API_KEY": "your-openai-key",
        "ANTHROPIC_API_KEY": "your-anthropic-key",
        "OPENROUTER_API_KEY": "your-openrouter-key"
      }
    }
  }
}

Environment Variables

  • OPENAI_API_KEY - Your OpenAI API key
  • ANTHROPIC_API_KEY - Your Anthropic API key
  • OPENROUTER_API_KEY - Your OpenRouter API key

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector:

npm run inspector

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

Recent Updates

Claude 3 and 3.5 Series Support (March 2024)

  • Added support for latest Claude models:
    • Claude 3 Series (Haiku, Sonnet, Opus)
    • Claude 3.5 Series (Haiku, Sonnet)

Unlimited Memory Retrieval

  • Added support for retrieving unlimited conversation history
  • Use { "limit": null } with the get_memory tool to retrieve all stored memories
  • Use { "limit": n } to retrieve the n most recent memories
  • Default limit is 10 if not specified
No tools information available.

Mirror of

image-generation mcp-server
View Details

Secure MCP server for analyzing Excel files with oletools

oletools mcp-server
View Details

Mirror of

bigquery mcp-server
View Details

MCPHubs is a website that showcases projects related to Anthropic's Model Context Protocol (MCP)

mcp mcp-server
View Details
Dealx
Dealx by DealExpress

-

dealx mcp-server
View Details

Google Analytics MCP server for accessing analytics data through tools and resources

google-analytics mcp-server
View Details

A Python-based MCP server that lets Claude run boto3 code to query and manage AWS resources. Execute powerful AWS operations directly through Claude with proper sandboxing and containerization. No need for complex setups - just pass your AWS credentials and start interacting with all AWS services.

aws mcp-server
View Details