Enables containerized deployment of the MCP server, supporting both SSE and stdio transport methods
Used for configuration management through environment variables to set up connections to LLM providers and databases
Supports integration with n8n workflow automation platform, with specific configuration guidance for container networking
Allows using Ollama's local language models as an alternative provider for generating embeddings and handling memory operations
Enables AI agents to utilize OpenAI's models for generating embeddings and providing language model capabilities for memory operations
Used as the vector database backend for storing and retrieving memories with semantic search capabilities
Provides a managed PostgreSQL database solution with vector storage capabilities for memory persistence
A template implementation of the Model Context Protocol (MCP) server integrated with Mem0 for providing AI agents with persistent memory capabilities.
Use this as a reference point to build your MCP servers yourself, or give this as an example to an AI coding assistant and tell it to follow this example for structure and code correctness!
Overview
This project demonstrates how to build an MCP server that enables AI agents to store, retrieve, and search memories using semantic search. It serves as a practical template for creating your own MCP servers, simply using Mem0 and a practical example.
The implementation follows the best practices laid out by Anthropic for building MCP servers, allowing seamless integration with any MCP-compatible client.
Features
The server provides three essential memory management tools:
save_memory
: Store any information in long-term memory with semantic indexingget_all_memories
: Retrieve all stored memories for comprehensive contextsearch_memories
: Find relevant memories using semantic search
Prerequisites
- Python 3.12+
- Supabase or any PostgreSQL database (for vector storage of memories)
- API keys for your chosen LLM provider (OpenAI, OpenRouter, or Ollama)
- Docker if running the MCP server as a container (recommended)
Installation
Using uv
- Install uv if you don't have it:
- Clone this repository:
- Install dependencies:
- Create a
.env
file based on.env.example
: - Configure your environment variables in the
.env
file (see Configuration section)
Using Docker (Recommended)
- Build the Docker image:
- Create a
.env
file based on.env.example
and configure your environment variables
Configuration
The following environment variables can be configured in your .env
file:
Variable | Description | Example |
---|---|---|
TRANSPORT | Transport protocol (sse or stdio) | sse |
HOST | Host to bind to when using SSE transport | 0.0.0.0 |
PORT | Port to listen on when using SSE transport | 8050 |
LLM_PROVIDER | LLM provider (openai, openrouter, or ollama) | openai |
LLM_BASE_URL | Base URL for the LLM API | https://api.openai.com/v1 |
LLM_API_KEY | API key for the LLM provider | sk-... |
LLM_CHOICE | LLM model to use | gpt-4o-mini |
EMBEDDING_MODEL_CHOICE | Embedding model to use | text-embedding-3-small |
DATABASE_URL | PostgreSQL connection string | postgresql://user:pass@host:port/db |
Running the Server
Using uv
SSE Transport
The MCP server will essentially be run as an API endpoint that you can then connect to with config shown below.
Stdio Transport
With stdio, the MCP client iself can spin up the MCP server, so nothing to run at this point.
Using Docker
SSE Transport
The MCP server will essentially be run as an API endpoint within the container that you can then connect to with config shown below.
Stdio Transport
With stdio, the MCP client iself can spin up the MCP server container, so nothing to run at this point.
Integration with MCP Clients
SSE Configuration
Once you have the server running with SSE transport, you can connect to it using this configuration:
Note for Windsurf users: Use
serverUrl
instead ofurl
in your configuration:
Note for n8n users: Use host.docker.internal instead of localhost since n8n has to reach outside of it's own container to the host machine:
So the full URL in the MCP node would be: http://host.docker.internal:8050/sse
Make sure to update the port if you are using a value other than the default 8050.
Python with Stdio Configuration
Add this server to your MCP configuration for Claude Desktop, Windsurf, or any other MCP client:
Docker with Stdio Configuration
Building Your Own Server
This template provides a foundation for building more complex MCP servers. To build your own:
- Add your own tools by creating methods with the
@mcp.tool()
decorator - Create your own lifespan function to add your own dependencies (clients, database connections, etc.)
- Modify the
utils.py
file for any helper functions you need for your MCP server - Feel free to add prompts and resources as well with
@mcp.resource()
and@mcp.prompt()
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
A Model Context Protocol server that provides AI agents with persistent memory capabilities through Mem0, allowing them to store, retrieve, and semantically search memories.
Related MCP Servers
- -securityAlicense-qualityA Model Context Protocol server that enhances AI agents by providing deep semantic understanding of codebases, enabling more intelligent interactions through advanced code search and contextual awareness.Last updated -48PythonMIT License
- -securityAlicense-qualityA Model Context Protocol server that integrates AI assistants with Mem0.ai's persistent memory system, allowing models to store, retrieve, search, and manage different types of memories.Last updated -9PythonMIT License
- -securityAlicense-qualityA Model Context Protocol (MCP) server that provides persistent memory and context management for AI systems through a structured 5-phase optimization workflow.Last updated -TypeScriptMIT License
- AsecurityFlicenseAqualityA Model Context Protocol server that provides persistent memory capabilities for AI systems, enabling true continuity of consciousness across conversations through episodic, semantic, procedural, and strategic memory types.Last updated -244JavaScript