Memory server for AI Chat with MCP interface
About
This is the MCP server with memory interface. It can be used with an AI Chat tool as a memory service
Details
- Author
- Gelembjuk
- Downloads
- 234
- Categories
- Knowledge Base
Jump to
- Exposes remember and recall MCP tools.
- Stores chat messages with role and content.
- Returns a summary of previous conversations.
- Runs as a FastAPI server with SSE transport.
- Includes a CLI for manual testing and debugging.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- 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
Memory server for AI Chat with MCP interfaceCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, install uv, create a virtual environment, run uv sync, then start the server with fastapi run mcp_server.py --port 8001. The server uses SSE transport and is accessible at http://localhost:8001/mcp. A CLI (python manager.py) is provided for testing and debugging, supporting commands like remember, recall, clear-memory, patch-memories, and history-dump.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"memory server for ai chat with mcp interface": {
"cleverchatty-memory": {
"command": "uv",
"args": [
"venv"
]
}
}
}
}McpServers
{
"cleverchatty-memory": {
"command": "uv",
"args": [
"venv"
]
}
}Memory server for AI Chat with MCP interface
This is an example of the memory server for AI chat. It follows the interface supported by the tool CleverChatty.
The interface for the MCP server is:
{
"tools": [
{
"name": "remember",
"description": "Remember a chat message to extract a context later for the memory",
"inputSchema": {
"properties": {
"role": { "type": "string" },
"message": { "type": "string" }
},
"required": ["role", "message"]
}
},
{
"name": "recall",
"description": "Returns the summary of the previous conversations",
"inputSchema": {
"properties": {
},
"required": []
}
}
]
}
This tool can be used together with the CleverChatty CLI to create an AI chat with memory. The server will remember the messages and return the summary of the previous conversations when requested.
How to run the server
1. Clone the repository
git clone git@github.com:Gelembjuk/cleverchatty-memory.git
cd cleverchatty-memory
2. Install uv if not already installed
curl -Ls https://astral.sh/uv/install.sh | sh
3. Create the virtual environment
uv venv
4. Activate the virtual environment on Linux/macOS (can be different on other platforms)
source .venv/bin/activate
5. Install the dependencies
uv sync
6. Run the server
fastapi run mcp_server.py --port 8001
This will start the MCP server with SSE transport on port 8001. You can change the port by modifying the --port argument. It will be accessible by the URL http://localhost:8001/mcp. You can also use the --host argument to change the host. By default, it will be accessible only from localhost. You can change it to --host 0.0.0.0 to make it accessible from any IP address.
Test ad debug
This tool contains also the CLI to test the server.
python manager.py COMMAND
Examples:
python manager.py clear-memory
python manager.py remember "user" "Some message from user"
python manager.py remember "assistant" "Some response from assistant"
python manager.py patch-memories
python manager.py recall
python manager.py history-dump
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
