🇨🇳 中文文档
Mem0 MCP Server Setup
This is a local MCP server for Mem0, allowing you to store and search memories directly from Cursor.
Prerequisites
- Python 3.10+
- A Mem0 API Key (Get one at https://app.mem0.ai/)
Installation
- Install Dependencies:
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt- Configure API Key:
🚀 Recommended: Set MEM0_API_KEY directly in the env section of mcp.json (no .env file needed, see Cursor config below).
Or use .env file:
- Copy
.env.exampleto.env:
cp .env.example .env- Open
.envand replaceyour_mem0_api_key_herewith your actual Mem0 API Key.
Cursor Configuration (mcp.json)
Add the following entry to your Cursor mcp.json file (usually located at ~/.cursor/mcp.json or accessible via Cursor Settings > MCP):
{
"mcpServers": {
"mem0": {
"command": "/Users/alexnear/Documents/mem0MCP/venv/bin/python",
"args": [
"/Users/alexnear/Documents/mem0MCP/server.py"
],
"env": {
"MEM0_API_KEY": "your_api_key_here"
}
}
}
}Note:
- 🚀 Preferred: Set
MEM0_API_KEYdirectly in theenvsection ofmcp.json- FastMCP passes it to the server process automatically. - Alternative: Use
.envfile (loaded viapython-dotenv). Ensure server runs from the directory containing.env. - Ensure the python command points to the python environment where you installed the requirements (e.g., if you used a venv, point to
venv/bin/python).
Tools Provided
add_memory: Stores messages/interactions.search_memories: Semantically searches stored memories (v2).
