MemGPT MCP Server

What is MemGPT MCP Server?

MemGPT MCP Server is a TypeScript-based MCP server that implements a memory system for large language models. It provides tools for chatting with different LLM providers (OpenAI, Anthropic, OpenRouter, Ollama) while maintaining conversation history, making it ideal for developers who need persistent memory in LLM interactions.

How to use MemGPT MCP Server?

Install dependencies with npm install, then build with npm run build. For Claude Desktop, add a server configuration to claude_desktop_config.json pointing to the built index.js and set the required environment variables (OPENAI_API_KEY, ANTHROPIC_API_KEY, OPENROUTER_API_KEY). Use the provided tools—chat, get_memory, clear_memory, use_provider, and use_model—to interact with LLMs and manage conversation memory.

Key features of MemGPT MCP Server

• Chat with multiple LLM providers (OpenAI, Anthropic, OpenRouter, Ollama)
• Retrieve conversation history with optional pagination (limit or unlimited)
• Clear all stored conversation memory
• Switch between LLM providers persistently
• Switch to provider‑specific models (e.g., Claude 3/3.5, GPT‑4, Ollama local models)

Use cases of MemGPT MCP Server

• Building LLM‑powered applications with persistent conversation memory
• Experimenting with different LLM providers and models in one interface
• Debugging or testing tool use with memory management
• Prototyping memory‑enabled agents or chatbots

FAQ from MemGPT MCP Server

Which LLM providers are supported?

OpenAI, Anthropic, OpenRouter, and Ollama are supported. Provider selections are persisted.

How do I retrieve conversation history?

Use the get_memory tool. Pass an optional limit parameter (number) to retrieve the N most recent memories, or limit: null for unlimited retrieval. Results are chronological with timestamps; default limit is 10.

How do I clear memory?

Use the clear_memory tool. It removes all stored conversation history.

What environment variables are needed?

You may need OPENAI_API_KEY, ANTHROPIC_API_KEY, and/or OPENROUTER_API_KEY depending on which providers you plan to use.

How can I debug the server?

Use the MCP Inspector by running npm run inspector. The Inspector provides a URL for browser‑based debugging tools.