README.md•3.13 kB
# Store MCP Server
A Model Context Protocol (MCP) server that enables AI agents to store and retrieve information persistently.
## Project Structure
```
store_mcp/
├── README.md # This file
├── pyproject.toml # Project dependencies and configuration
├── src/
│ └── store_mcp/
│ ├── __init__.py # Package initialization
│ ├── server.py # Main MCP server implementation
│ └── storage.py # Storage backend (JSON/SQLite)
└── tests/
├── __init__.py
└── test_server.py # Unit tests
```
## Features
- **Store Information**: Save key-value pairs or structured data
- **Retrieve Information**: Query stored data by key or search criteria
- **List Keys**: View all available stored keys
- **Delete Information**: Remove stored data when no longer needed
- **Persistent Storage**: Data persists across sessions
## Installation
```bash
# Install dependencies
pip install -e .
```
## Usage
```bash
# Run the MCP server
python -m store_mcp.server
```
## MCP Tools
The server exposes the following tools to AI agents:
- `store_data`: Store information with a key
- `retrieve_data`: Retrieve information by key
- `list_keys`: List all stored keys
- `delete_data`: Delete stored information by key
- `search_data`: Search stored information by pattern or content
## Configuration
### MCP Client Configuration
To use this server with an MCP client (like Claude Desktop), add it to your MCP settings configuration file:
**For Claude Desktop on MacOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
**For Claude Desktop on Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
```json
{
"mcpServers": {
"store": {
"command": "python",
"args": [
"-m",
"store_mcp.server"
],
"env": {
"PYTHONPATH": "/absolute/path/to/store_mcp/src"
}
}
}
}
```
**Alternative using uvx** (if installed via pip):
```json
{
"mcpServers": {
"store": {
"command": "uvx",
"args": [
"--from",
"/absolute/path/to/store_mcp",
"python",
"-m",
"store_mcp.server"
]
}
}
}
```
### Storage Configuration
The server uses a local file-based storage system (JSON) located at:
- **Default**: `~/.store_mcp/data.json`
To use a custom storage location, modify `server.py` and initialize Storage with a custom path:
```python
storage = Storage("/path/to/custom/data.json")
```
### Environment Variables
You can set the following environment variables:
- `STORE_MCP_PATH`: Custom path for the storage file (default: `~/.store_mcp/data.json`)
Example configuration with custom storage path:
```json
{
"mcpServers": {
"store": {
"command": "python",
"args": ["-m", "store_mcp.server"],
"env": {
"PYTHONPATH": "/absolute/path/to/store_mcp/src",
"STORE_MCP_PATH": "/custom/path/to/storage.json"
}
}
}
}
```
## Development
```bash
# Run tests
pytest tests/
```
## Requirements
- Python 3.10+
- mcp library