Simple

Provides a local MCP server to manage items and AI-assisted analysis with a REST/CLI interface.

python

0

GitHub Stars

python

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "chirayupatel9-simple_mcp": {
      "command": "python",
      "args": [
        "app/mcp_server.py"
      ]
    }
  }
}

You run a local MCP server that lets you manage data items and run AI-powered analyses entirely on your machine. It uses a Python backend with FastAPI, stores data in a local folder, and exposes an MCP-compliant interface so AI assistants can interact with your data and models.

How to use

Install and start the MCP server on your machine, then connect a client that supports MCP to perform data operations and AI analyses. You will manage items, perform searches, analyze text with local AI models, and run batch analyses, all through straightforward commands and restful endpoints. Use the server to keep data in a local data store while leveraging embedded AI capabilities for similarity search, text analysis, and model switching.

How to install

Prerequisites you need before you begin:

Python 3.8 or higher
pip (Python package installer)
Sufficient RAM for AI models (2-4GB recommended)

Step-by-step setup and run flow you should follow:

Clone or download the project to your local machine
Install dependencies with pip
Run the FastAPI server either via the provided run script or directly with uvicorn

MCP Server Details

{
  "mcpServers": [
    {
      "name": "simple_mcp",
      "type": "stdio",
      "command": "python",
      "args": ["app/mcp_server.py"]
    }
  ]
}

Run the server

Start the MCP server locally using the following command. The server will load its MCP tools and start listening for requests from your MCP client.

python app/mcp_server.py

Usage with a client

Once the MCP server is running, connect a compatible MCP client to send commands to manage items and perform AI analyses. You can create, read, update, and delete items, perform full-text and AI-powered searches, and run text analyses or similarity checks against your local data.

Additional setup tips

If you prefer to run the server via a standard web-friendly entry point, you can also start a FastAPI instance and access the interactive docs at /docs and /redoc after the server is up.

Available tools

get_all_items

Retrieve all items from the data store

get_item_by_id

Get a specific item by its ID

create_item

Create a new item with name, description, and category

update_item

Update an existing item by ID

delete_item

Delete an item by ID

search_items

Search items by query string

get_ai_model_info

Get information about the loaded AI model

change_ai_model

Change the AI model type and name

analyze_text

Analyze text using the AI model

analyze_all_items

Analyze all items using the AI model

find_similar_items

Find items similar to a query using AI embeddings

analyze_single_item

Analyze a specific item using the AI model

smart_search

Smart search combining traditional search with AI similarity