MCP Playground

Requirements

• Python 3.13

• uv package manager

• SQLite3

Related MCP server: DB MCP (HR CSV → SQLite)

Installation

1. Clone the repository

   git clone <repository-url>
   cd mcp_playground

2. Install dependencies with uv

   uv sync

3. Setup the SQLite database

   1. Create a new SQLite database file using the provided schema.

   cd db

   sqlite3 database.db < schema.sql

   2. Insert dummy data into the database.

   sqlite3 database.db < insert_data.sql

4. Start the venv (if you want to start the server manually)

   source .venv/bin/activate

Usage

Starting the server

The server currently uses IO for communication. It is not meant to be started manually, instead it should be accessed through an MCP client.

Implemented Functions

The following functions are implemented in the server:

1. db_schema (resource)

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

2. get_users (tool)

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

3. get_all_employee_profiles (tool)

   • Retrieves all employee profiles

4. send_email (tool)

   • Sends an email using mailtrap.

   • Requires API-key in .env file:

     MAILTRAP_API_TOKEN=your_mailtrap_api_key

5. propose_team_for_project (prompt)

   • Given a project description and team size, proposes a team of employees best suited for the project based on their skills and experience.

Integration with Claude Desktop as the MCP client

Add the following configuration to your MCP client (e.g., Claude Desktop):

• Settings → Developer → Edit config → claude_desktop_config.json

• mcpServers: The server name, in this case not-solita-corp.

• command: The ABSOLUTE path to the uv executable on your system.

• args: The arguments to start the MCP server, including the ABSOLUTE path to the mcp_playground directory.

• Note: Windows paths use backslashes (\).

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