Metadata-Version: 2.4
Name: geaicontext
Version: 1.0.5
Summary: Context and Memory MCP
Requires-Python: >=3.12
Description-Content-Type: text/markdown
Requires-Dist: fastmcp>=2.14.0
Requires-Dist: motor>=3.7.1
Requires-Dist: redis>=7.1.0

# Daxia OpenAPI Client based MCP

[![Python Version](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)
[![FastMCP](https://img.shields.io/badge/fastmcp-2.14.0+-green.svg)](https://pypi.org/project/fastmcp/)
[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
[![uv](https://img.shields.io/badge/uv-managed-blueviolet.svg)](https://github.com/astral-sh/uv)

A [FastMCP](https://pypi.org/project/fastmcp/) server that dynamically creates MCP tools from OpenAPI specifications, enabling seamless integration with any OpenAPI-compliant API.

## Table of Contents

- [Features](#features)
- [Dependencies](#dependencies)
- [Installation](#installation)
- [Testing](#testing)
- [Usage](#usage)
- [Examples](#examples)
- [How It Works](#how-it-works)
- [License](#license)

## Features

- 🚀 **Dynamic Tool Generation**: Automatically creates MCP tools from OpenAPI specifications
- 🔐 **OAuth2 Authentication**: Automatic token retrieval from Daxia platform
- 🌐 **Flexible Configuration**: Environment-based configuration for easy deployment
- 📝 **OpenAPI 3.x Support**: Works with any valid OpenAPI 3.x specification
- ⚡ **FastMCP Powered**: Built on the high-performance FastMCP framework

## Dependencies

This project requires Python 3.12 or higher and uses the following dependencies:

- **[fastmcp](https://pypi.org/project/fastmcp/)** (>=2.14.0) - FastMCP framework for building MCP servers
- **[httpx](https://www.python-httpx.org/)** (>=0.28.1) - Modern HTTP client for making API requests
- **[requests](https://requests.readthedocs.io/)** (>=2.32.5) - HTTP library for additional compatibility

All dependencies are managed using [uv](https://github.com/astral-sh/uv) for fast and reliable package management.

## Installation

This project uses [uv](https://github.com/astral-sh/uv) for dependency management.

### Prerequisites

1. **Python 3.12 or higher**
   ```bash
   python --version  # Should be 3.12 or higher
   ```

2. **Install uv**
   ```bash
   curl -LsSf https://astral.sh/uv/install.sh | sh
   ```

### Installation Steps

1. **Clone the repository**
   ```bash
   git clone <repository-url>
   cd daxiamcp
   ```

2. **Install the project**
   ```bash
   uv pip install -e .
   ```
   
   This will:
   - Install all required dependencies
   - Create the `daxiamcp` command-line tool
   - Make the project available for development

3. **Verify the installation**
   ```bash
   daxiamcp --help
   ```

### Alternative: Using uvx

You can run the tool directly without installation using `uvx`:

```bash
uvx daxiamcp
```

This is particularly useful for testing or running the examples without a full installation.

## Testing

This project uses [pytest](https://docs.pytest.org/) for testing with [pytest-cov](https://pytest-cov.readthedocs.io/) for coverage reporting.

### Install Dev Dependencies

Sync the project with dev dependencies:

```bash
uv sync --group dev
```

### Run Tests

Run all tests:

```bash
uv run pytest
```

Run tests with verbose output:

```bash
uv run pytest -v
```

### Run Tests with Coverage

Generate a coverage report in the terminal:

```bash
uv run pytest --cov=src/geaicontext --cov-report=term-missing
```

Generate an HTML coverage report:

```bash
uv run pytest --cov=src/geaicontext --cov-report=html
```

The HTML report will be generated in the `htmlcov/` directory. Open `htmlcov/index.html` in your browser to view the detailed coverage report.

### Run Specific Tests

Run tests in a specific file:

```bash
uv run pytest tests/test_context.py
```

Run a specific test function:

```bash
uv run pytest tests/test_context.py::test_function_name -v
```

## Linting (Pylint)

This project uses [Pylint](https://pylint.readthedocs.io/) for code quality checks and linting.

### Install Dev Dependencies

Sync the project with dev dependencies:

```bash
uv sync --group dev
```

### Run Pylint

Run Pylint on the source code:

```bash
uv run pylint src/geaicontext
```

Run Pylint on both source code and tests:

```bash
uv run pylint src/geaicontext tests
```

Pylint automatically reads its configuration from [`pyproject.toml`](pyproject.toml:28), including the Python version target and path settings.

## Usage

The `daxiamcp` command-line tool creates a FastMCP server from an OpenAPI specification.

### Configuration

Configure the server using the following environment variables:

| Variable | Default | Description |
|----------|---------|-------------|
| `API_BASE_URL` | `https://api-sandbox.daxiaplatform.com/sandbox/api/v1` | The base URL of the API |
| `OPENAPI_SPEC_URL`| `http://localhost/local/openapi/daXia1.json` | The URL of the OpenAPI specification |
| `SERVER_NAME` | `Daxia API` | The name of the MCP server |
| `DAXIA_AUTH_URL` | `https://auth-sbx.daxiaplatform.com/oauth2/token` | OAuth2 token endpoint URL |
| `DAXIA_CLIENT_ID` | (has default) | OAuth2 client ID for Daxia authentication |
| `DAXIA_AUTH_BASIC` | (has default) | Base64-encoded Basic auth string for OAuth2 token request |

### Running the Server

The server automatically retrieves an OAuth2 access token from the Daxia platform on startup. You can customize the configuration by setting environment variables:

**Basic Usage (using defaults):**
```bash
daxiamcp
```

**Custom Configuration:**
```bash
export API_BASE_URL="http://localhost:3000/v1"
export OPENAPI_SPEC_URL="http://localhost/local/openapi/gal-inq.json"
export SERVER_NAME="Galicia Inquiries API"
daxiamcp
```

### Authentication

The server uses **OAuth2 Client Credentials** flow to authenticate with the Daxia platform:

1. On startup, the server requests an access token from `DAXIA_AUTH_URL`
2. The token is obtained using the client credentials (`DAXIA_CLIENT_ID` and `DAXIA_AUTH_BASIC`)
3. The access token is automatically included in all API requests as a Bearer token
4. If token retrieval fails, the server will use `INVALID_TOKEN` and log an error

**Custom OAuth2 Credentials:**
```bash
export DAXIA_CLIENT_ID="your-client-id"
export DAXIA_AUTH_BASIC="your-base64-encoded-credentials"
export DAXIA_AUTH_URL="https://your-auth-server.com/oauth2/token"
daxiamcp
```

## Examples

The `examples` directory contains sample configurations for different services. Each example is a JSON file that can be used with MCP-compatible tools.

### Example Configuration

Here's an example configuration for the Galicia Inquiries API (`examples/gal-mock/gal-inq.json`):

```json
{
    "mcpServers": {
        "daXia": {
            "command": "uvx",
            "args": [
                "daxiamcp"
            ],
            "env": {
                "SERVER_NAME": "daXia API",
                "DAXIA_AUTH_URL": "https://auth-sbx.daxiaplatform.com/oauth2/token",
                "DAXIA_CLIENT_ID": "clientid",
                "DAXIA_AUTH_BASIC": "your-base64-encoded-credentials",
                "OPENAPI_SPEC_URL": "http://localhost/local/openapi/daXia1.json",
                "API_BASE_URL": "https://api-sandbox.daxiaplatform.com/sandbox/api/v1"
            }
        }
    }
}
```

### Using Examples

1. **Navigate to the examples directory:**
   ```bash
   cd examples/gal-mock
   ```

2. **Use the configuration with your MCP client:**
   - Copy the configuration to your MCP client's configuration file
   - The client will automatically start the server using `uvx daxiamcp`
   - The server will use the environment variables defined in the `env` section

3. **Available Examples:**
   - `gal-mock/gal-inq.json` - Galicia Inquiries API example
   - Add more examples as needed for different services

## How It Works

The Daxia OpenAPI MCP server follows this workflow:

```mermaid
graph LR
    A[Daxia OAuth2] --> B[Access Token]
    B --> C[HTTP Client]
    D[OpenAPI Spec] --> E[Parse Specification]
    E --> F[Generate MCP Tools]
    C --> G[FastMCP Server]
    F --> G
    G --> H[MCP Client]
    H --> I[API Requests]
    I --> J[Target API]
```

1. **OAuth2 Authentication**: The server retrieves an access token from the Daxia OAuth2 endpoint using client credentials
2. **Specification Loading**: The server fetches the OpenAPI specification from the provided URL
3. **Tool Generation**: Each API endpoint is converted into an MCP tool with appropriate parameters
4. **Server Initialization**: FastMCP server is initialized with the generated tools and authenticated HTTP client
5. **Request Handling**: When a tool is invoked, the server makes the corresponding API request with the Bearer token
6. **Response Processing**: API responses are formatted and returned to the MCP client

### Architecture

- **`main.py`**: Entry point that initializes the FastMCP server
- **OAuth2 Client**: Retrieves access tokens from Daxia authentication endpoint
- **OpenAPI Parser**: Reads and validates the OpenAPI specification
- **Tool Generator**: Creates MCP tools from API endpoints
- **HTTP Client**: Handles API requests with Bearer token authentication
- **FastMCP Integration**: Manages the MCP protocol communication

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
