MCP Project

Provides a full MCP server enabling Claude to manage appointments via CRUD operations backed by FastAPI and PostgreSQL.
  • python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months 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": {
    "samuelr2112-mcp-project": {
      "command": "python3",
      "args": [
        "mcp_server.py"
      ]
    }
  }
}

You can run a complete MCP server that talks to Claude using a FastAPI backend and PostgreSQL, enabling Claude to manage appointments via create, read, update, and delete operations. This setup provides structured, real-time MCP interactions with a robust backend and clear, professional responses for business use.

How to use

You interact with the MCP server through an MCP client to perform appointment operations. You can create new appointments, retrieve the full list of appointments, update existing entries, or delete items as needed. The server responds with consistent date handling and clear error messages, making it straightforward to integrate into business workflows.

How to install

Prerequisites: make sure you have Docker and Docker Compose installed, and you have Python available for local MCP server entry. You should also have a terminal or shell ready to run commands.

Follow these steps to install and start the MCP server locally.

# 1) Prepare the environment
# Create and activate a Python virtual environment (optional but recommended)
python3 -m venv venv
source venv/bin/activate

# 2) Start the Docker-based services (PostgreSQL and any required containers)
docker-compose up --build -d

docker-compose ps

# 3) Start the MCP server that communicates with Claude
python3 mcp_server.py

Additional sections

Configuration and startup notes: The MCP server uses a stdio transport for Claude integration and exposes CRUD endpoints for appointment management. The backend persists data in PostgreSQL and is orchestrated via Docker Compose for reliable restarts and isolation.

API endpoints you can expect to use through the MCP client include creating, listing, updating, and deleting appointments. The system handles ISO 8601 date strings and formats output consistently for business use.

Shutdown and cleanup: When you need to stop everything, stop the MCP server with Ctrl+C in the terminal running it, then bring down the Docker services.

Notes on deployment: Use version control to track changes and push updates to your origin branch as you iterate on the MCP integration.

Available tools

Create Appointment

Create a new appointment via the MCP endpoint and receive a confirmation with the assigned identifier and timestamp.

List Appointments

Retrieve all stored appointments, including IDs, dates, and details, for display in client applications.

Update Appointment

Modify an existing appointment by ID, changing details or date, with feedback on success or failure.

Delete Appointment

Remove an appointment by its ID and confirm deletion in the response.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
MCP Project MCP Server - samuelr2112/mcp-project | VeilStrat