mcpField
W
What?

What?

Local
github.com/bkakadiyaAI & Agents1Updated 80w ago
Repository

About What?

What? is a sample application demonstrating an AI agent using MCP servers to connect to REST APIs, PostgreSQL, and document storage. It includes setup guidance and a Claude Desktop configuration example.

Key features

  1. 01REST API connectivity
  2. 02PostgreSQL database access
  3. 03Document storage connectivity
  4. 04Sample financial transaction data setup
  5. 05Claude Desktop configuration example

Use cases

  1. 01Explore an agent connecting to REST services and data stores
  2. 02Configure Claude Desktop to use the sample MCP tools

MCP support

The sample uses MCP servers to connect an agent with REST APIs, a PostgreSQL database, and document storage. It provides a sample Claude Desktop configuration for exposing its tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

What?

Application Architecture

Sample application showing Agentic AI using MCP Server connecting to REST API, PostgreSQL Database and Document Storage

Setup

UV Installation and Setup

  1. Install UV
    To install UV, run the following command:

    pip install uv

  2. Verify Installation
    Confirm that UV is installed by running:

    uv --version

Using pyproject.toml

Setting Up a Virtual Environment and Installing Dependencies

  1. Create a Virtual Environment
    Run the following command to create a virtual environment:

    python -m venv venv

  2. Activate the Virtual Environment

    • On Windows: 
      venv\Scripts\activate
    • On macOS/Linux: 
      source venv/bin/activate

  3. Install Dependencies from pyproject.toml
    Use pip to install dependencies specified in the pyproject.toml file:

    pip install .

  4. Verify Installation
    Ensure all dependencies are installed correctly:

    pip list

  5. Run Test Cases
    Ensure all test cases are passed using pytest:

    pytest

Populate Financial Txn Data

  1. Run the Script to Populate Data
    Execute the following command to populate sample financial transaction data: 
    python util/populate_data.py

Configure MCP Client - Claude for Windows

  1. Locate the Sample Configuration File
    Use the provided config/sample_claude_desktop_config.json file as a template.

  2. Copy the Configuration File
    Place the file in the following directory:

    ~\AppData\Roaming\Claude

  3. Rename the File
    Rename the file to claude_desktop_config.json.

  4. Update Configuration Details

    • Open the claude_desktop_config.json file in a text editor.
    • Update the Alpha Vantage API Key with your key.
    • Update the Database Connection Details with the appropriate credentials and connection string.

Restart Claude Desktop

Restart Claude Desktop, you might have to kill tasks from Task manager. Note that once you restart it,

  1. You should be able to see number of tools along with hammer icon.
  2. This will start python program for each tool in background.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.