ops

ops-mcp-server is a Python-based MCP server built around the uv dependency management tool. It exposes a suite of remote server inspection and network management tools, including memory and OS details, process monitoring, service status checks, firewall and SSH risk assessments, log analysis, and network device management features. The server is designed to run locally or remotely via UV’s orchestration, enabling batch operations and remote inspections across multiple devices. Users can discover available tools using the list_available_tools capability and then invoke the desired tool against targeted hosts or devices. The configuration in the README demonstrates how to point UV at your project and expose the main.py entrypoint as the MCP server module, allowing clients to request tool results via MCP protocols.

Prerequisites:

• Python 3.10 or higher
• uv dependency management tool (via the provided install script in uv or your system)

Setup steps:

1. Install uv (Python dependency/virtual environment manager used by this project):

curl -LsSf https://astral.sh/uv/install.sh | sh

2. Create and activate a Python virtual environment:

uv venv .venv
source .venv/bin/activate  # Linux/macOS
# or
.\\.venv\\Scripts\\activate   # Windows

3. Install project dependencies:

uv pip install -r requirements.txt

4. Ensure Python 3.10+ is installed (as referenced in the docs). You may also install additional dependencies specified in pyproject.toml if needed.
5. Place the project in a directory and verify main.py exists as the MCP entrypoint. Adjust the path in the MCP server configuration accordingly.

Tips and considerations:

• The MCP configuration example uses UV with --directory pointing to YOUR_PROJECT_PATH_HERE and runs main.py. Replace YOUR_PROJECT_PATH_HERE with the actual path to your ops-mcp-server project.
• The server is marked as disabled by default in the example; enable it when ready to accept MCP requests.
• Tools include both server-side inspection capabilities and network/device management features. Use list_available_tools to discover what’s exposed before attempting operations.
• If you run into environment issues, ensure the virtual environment is activated (source .venv/bin/activate) and that Python 3.10+ is being used.
• For remote operations, ensure SSH/remote access permissions are correctly configured and that the uv wrapper can reach remote endpoints.
• You can extend or modify main.py to tailor the toolset or add new capabilities; update the MCP configuration to expose new tools as needed.