Explorium

🚀 Explorerium MCP Server

The Explorerium MCP Server is a Model Context Protocol (MCP) server designed to interact with the Explorium API, enabling AI assistants to access Explorium's enterprise data and prospects lookup capabilities.

🚀 Quick Start

The Explorerium MCP Server is a Model Context Protocol (MCP) server for interacting with the Explorium API. It allows AI assistants to access Explorium's enterprise data and prospects lookup features.

📦 Installation

To install the Explorerium MCP Server, run the following command:

pip install explorium-mcp-server

🛠️ Setting up the Development Environment

1. Clone the project repository:

git clone https://github.com/explorium-ai/mcp-server.git
cd mcp-server

2. Install the dependencies:

pip install -r requirements.txt

3. Configure environment variables by editing the .env file:

APP_ENV=development
APP_SECRET=your-secret-key

💻 Local Run

Start the server by running the following command in the project root directory:

python src/explorium_mcp_server/__main__.py

💻 Usage with AI Assistants

Claude Desktop

To integrate the Explorerium MCP Server into Claude Desktop, follow these steps:

1. Install the necessary dependencies:

pip install python-dotenv requests

2. Create a new script and add the following code:

from explorium_mcp_server import tools

def main():
    # Initialize the MCP tool
    mcp_tool = tools.MCPTool()
    # Fetch data
    data = mcp_tool.fetch_data()
    print(data)

if __name__ == "__main__":
    main()

3. Run the script in the terminal:

python your_script.py

Tools

The Explorerium MCP Server provides the following tools:

• MCPTool: Used to interact with the Explorium API.
• DataParser: Used to parse and process data.

📁 Project Structure

explorer-mcp-server/
├── .env               # Local environment variable file
├── src/              # Source code directory
│   └── explorium_mcp_server/
│       ├── __init__.py      # Package initialization file
│       ├── __main__.py      # Program entry point
│       ├── models/          # Data models and architectures
│       └── tools/           # MCP tool implementation
├── tests/            # Test suite
├── Makefile         # Development shortcut file
└── README.md        # Project documentation

🚧 Development Workflow

1. Set up the environment as described above.
2. Modify the code and save the changes.
3. Format the code:

make format

4. Run the checks:

make lint

5. Execute the tests:

make test

🔄 Continuous Integration

The project uses GitHub Actions for continuous integration and delivery. The main workflow is located at .github/workflows/ci.yml, which performs the following actions:

1. Version Check: Ensure that the version number in pyproject.toml is updated before merging into the main branch.
2. Code Style Check: Use ruff for code style and format validation.
3. Testing: Execute the test suite and generate a coverage report.
4. Deployment: Push the commit tag to GitHub.

📦 Build and Release

Build the Package

1. Update the version number in pyproject.toml (required for each new version).
2. Run the build command:

uv build

This command will create a dist/ folder in the project root directory, containing the generated installation package.

Release to PyPI

1. Make sure twine is installed:

pip install twine

2. Upload the built package to PyPI:

twine upload dist/*

You need to provide your PyPI credentials or configure the .pypirc file.

Automatic Versioning and Tagging

When code is merged into the main branch, the CI workflow will automatically:

1. Create a tag for the repository using the version number in pyproject.toml.
2. Push the tag to GitHub.