Video Intelligence

MCP Server generated by mcp.ag2.ai

python

0

GitHub Stars

python

Language

7 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": {
    "ag2-mcp-servers-cloud-video-intelligence-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "\"{...}\"",
        "SECURITY": "\"API_KEY=XXXX\"",
        "CONFIG_PATH": "\"/path/to/mcp_config.json\""
      }
    }
  }
}

You run an MCP (Model Context Protocol) Server to expose a live API for a model context using a fixed OpenAPI spec. This server lets MCP clients interact with the specified API in a structured, protocol-friendly way, enabling reliable, testable, and scalable client-server communication for model-driven workflows.

How to use

Start the local MCP server in stdio mode to connect through standard input/output streams. You can connect an MCP client that speaks the MCP protocol to this server, enabling you to send requests and receive responses without running over the network. The server supports other transport modes as well, but stdio provides a straightforward development workflow.

How to install

Prerequisites: Python 3.9 or newer, and the Python package manager pip. You may also use the uv helper to install and run the development environment.

Clone the project. (Replace <repository-url> with the actual URL when you start.)
Change into the project directory.

3. Install dependencies in development mode. You have two equivalent options:
- Using the dedicated setup script that installs editable dev dependencies:

pip install -e ".[dev]"

- Or install directly in editable mode with the `uv` helper:

uv pip install --editable ".[dev]"

Both methods prepare the MCP server runtime and tooling for linting, testing, and analysis.

Run static checks and tests as needed during development (see the next section for commands).

Additional sections

Running the MCP server is done via the main script. For stdio mode, the command is: python mcp_server/main.py stdioConfigure the server with environment variables if you have a custom setup: - CONFIG\_PATH: Path to a JSON configuration file (for example, mcp\_server/mcp\_config.json). - CONFIG: A JSON string containing the configuration directly. - SECURITY: Environment variables related to security parameters (for example, API keys). Refer to the entry point in the script for details on loading these values.

Development and quality tooling include using ruff for linting/formatting, mypy for static typing checks, and pytest for tests. Use the following commands to work with these tools:

Linting: ruff check and formatting: ruff format.
Static analysis: ./scripts/static-analysis.sh.
Tests with coverage: ./scripts/test.sh or ./scripts/test-cov.sh for a combined report and cleanup.

Configuration, security, and notes

The server can be configured using environment variables or a configuration file. The most common approach is to supply a JSON config via CONFIG or CONFIG_PATH. If you need security controls, set appropriate keys or tokens in SECURITY as documented in the startup script. This server is designed to work with the OpenAPI-based MCP for the target API and can be extended to support additional transport modes or endpoints as needed.

Available tools

ruff

Lints and formats Python code to ensure consistency and quality.

mypy

Performs static type checking to catch type errors early.

pytest

Runs tests to verify functionality and regressions.

hatch

Builds and publishes the MCP project.

pre-commit

Enforces repository quality through hooks before commits.