MemGPT MCP Server
About
A TypeScript-based server that provides a memory system for Large Language Models (LLMs), allowing users to interact with multiple LLM providers while maintaining conversation history and offering tools for managing providers and model configurations.
Details
- Author
- Vic563
- Repository
- Vic563/Memgpt-MCP-Server
- GitHub stars
- 21
- Downloads
- 4
- Categories
- Developer Tools, AI, Knowledge Base, Other
Jump to
- 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)
Setting up with Highlight
Follow these steps to add this server as a custom Highlight plugin:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MemGPT MCP ServerCommand (node, npx, python, etc.)nodeArguments-
Argument 1
/path/to/memgpt-server/build/index.js
Environment-
OPENAI_API_KEY
your-openai-key -
ANTHROPIC_API_KEY
your-anthropic-key -
OPENROUTER_API_KEY
your-openrouter-key
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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"
}
}
}
}
- OPENAI_API_KEY - Your OpenAI API key
- ANTHROPIC_API_KEY - Your Anthropic API key
- OPENROUTER_API_KEY - Your OpenRouter API key
chat
Send a message to the current LLM provider. Takes a message parameter and supports multiple providers (OpenAI, Anthropic, OpenRouter, Ollama).
get_memory
Retrieve conversation history. Optional 'limit' parameter specifies number of memories to retrieve. Pass 'limit: null' for unlimited memory retrieval. Returns memories in chronological order with timestamps.
clear_memory
Clear conversation history by removing 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 for Anthropic, OpenAI, OpenRouter, and Ollama. Persists model selection.
- 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
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"memgpt mcp server": {
"env": {
"OPENAI_API_KEY": "your-openai-key",
"ANTHROPIC_API_KEY": "your-anthropic-key",
"OPENROUTER_API_KEY": "your-openrouter-key"
},
"args": [
"/path/to/memgpt-server/build/index.js"
],
"command": "node"
}
}
}Linux
{
"env": {
"OPENAI_API_KEY": "your-openai-key",
"ANTHROPIC_API_KEY": "your-anthropic-key",
"OPENROUTER_API_KEY": "your-openrouter-key"
},
"args": [
"/path/to/memgpt-server/build/index.js"
],
"command": "node"
}Macos
{
"env": {
"OPENAI_API_KEY": "your-openai-key",
"ANTHROPIC_API_KEY": "your-anthropic-key",
"OPENROUTER_API_KEY": "your-openrouter-key"
},
"args": [
"/path/to/memgpt-server/build/index.js"
],
"command": "node"
}Windows
{
"env": {
"OPENAI_API_KEY": "your-openai-key",
"ANTHROPIC_API_KEY": "your-anthropic-key",
"OPENROUTER_API_KEY": "your-openrouter-key"
},
"args": [
"/path/to/memgpt-server/build/index.js"
],
"command": "node"
}A server that provides a memory system for LLMs, enabling persistent conversations with various providers like OpenAI, Anthropic, and OpenRouter.
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.
-
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
- Optionallimitparameter to specify number of memories to retrieve
- Passlimit: nullfor unlimited memory retrieval
- Returns memories in chronological order with timestamps
clear_memory- Clear conversation history
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-haiku: Enhanced speed and cost-effectiveness
- claude-3.5-sonnet: Superior performance with computer interaction capabilities
To use with Claude Desktop, add the server config:
On MacOS:~/Library/Application Support/Claude/claude_desktop_config.jsonOn 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" } } } }
- OPENAI_API_KEY- Your OpenAI API key
- ANTHROPIC_API_KEY- Your Anthropic API key
- OPENROUTER_API_KEY- Your OpenRouter API key
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using theMCP Inspector:
The Inspector will provide a URL to access debugging tools in your browser.
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)
- Added support for retrieving unlimited conversation history
- Use{ "limit": null }with theget_memorytool to retrieve all stored memories
- Use{ "limit": n }to retrieve the n most recent memories
- Default limit is 10 if not specified
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
A persistent memory server for Large Language Models, designed to integrate with the Claude desktop application. It supports tiered memory, semantic search, and automatic memory management.
MCP (Model Context Protocol) server that exposes 70 tools spanning cognitive memory, working memory, sessions, agents, the L0–L3 knowledge hierarchy, orchestration tasks, and training pipelines. The server speaks stdio and is consumed by Claude Desktop, Claude Code, OpenCodex, and any MCP-aware client.
Hosted MCP memory across Claude Code, Cursor, ChatGPT and any MCP client. Community-hosted instance of the MIT-licensed MemPalace engine. EU-hosted, GDPR-compliant. Free tier with 200 memories.
User-owned memory for AI agents over remote MCP. Save, search, recall, update, and manage scoped memories across Copilot, Claude, ChatGPT, IDEs, and CLIs.
Server providing persistent multimodal context storage for LLM agents.
A framework for developing LLM applications with capabilities like tool usage, planning, and memory, based on the Qwen model.
Identity infrastructure for AI agents. Evolving behavioral profiles, experiential memory, self-correcting retrieval. Local-first, model-agnostic.
Open-source AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization
Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.
Local Work Model for AI agents that learns from real outcomes.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
