MCP Playground Server

A Python-based MCP server providing DB access tools and a Mailtrap email tool for client usage.

python

0

GitHub Stars

python

Language

6 months ago

First Indexed

3 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": {
    "jaanlavaerts-mcp_playground": {
      "command": "/path/to/user/.local/bin/uv",
      "args": [
        "--directory",
        "/path/to/user/mcp_playground",
        "run",
        "server.py"
      ],
      "env": {
        "MAILTRAP_API_TOKEN": "YOUR_MAILTRAP_API_KEY"
      }
    }
  }
}

You learn how to run and use a Python-based MCP server that exposes data access and utility tools through a lightweight client protocol. This server lets you fetch user lists, retrieve employee profiles, send test emails via Mailtrap, and generate recommended project teams from descriptions and skills.

How to use

You access the server through an MCP client. The server exposes a set of tools and endpoints that you can invoke from your client to perform common data tasks and utilities. Use the client to call the available tools, pass the required input, and receive structured results without needing to run server-side scripts locally.

How to install

Prerequisites you need before installation:

Python 3.13 is required.

The uv package manager is used to install dependencies and run the MCP server.

SQLite3 is required for the embedded database.

# Step 1: Prepare environment
# Install Python 3.13 (as available for your OS)

# Step 2: Install dependencies via uv (runtime package manager for this MCP setup)
uv sync

# Step 3: Initialize the database (schema and seed data)
# Create and populate the database using provided scripts
# Example paths shown for guidance

cd db
sqlite3 database.db < schema.sql
sqlite3 database.db < insert_data.sql

# Step 4: Optional virtual environment (activate if you want to run server manually)
source .venv/bin/activate

Additional setup notes

If you plan to connect with an MCP client, you can configure the client with the following example MCP server entry to start the local MCP runtime using the uv command.

{
  "mcpServers": {
    "mcp_demo": {
      "command": "/path/to/user/.local/bin/uv",
      "args": [
        "--directory",
        "/path/to/user/mcp_playground",
        "run",
        "server.py"
      ]
    }
  }
}

Available tools

db_schema

Returns the database schema by reading the schema.sql file.

get_users

Fetches a list of all user names from the users table in the database.

get_all_employee_profiles

Retrieves all employee profiles from the database.

send_email

Sends an email using Mailtrap. Requires MAILTRAP_API_TOKEN to be set.

propose_team_for_project

Proposes a team of employees best suited for a project based on its description and desired team size.