Trento MCP Server

Install in VS Code

This project is still in very early stages of development and may not be fully functional or stable. For now, it serves as a proof of concept and a starting point for building MCP servers that integrate with the Trento API.

The Trento MCP Server project introduces a Model Context Protocol (MCP) server implementation, enabling Trento to be used and configured as a tool for AI. Instead of interacting with the Trento server solely through the web UI, you can now interact with it directly from an AI, a chat interface, or an agent.

Features

  • OpenAPI-Driven Tool Generation:

    • The server uses the OpenAPI specification in api/openapi.json to automatically generate tools and endpoints, ensuring strong alignment between the API contract and implementation.

  • Security:

    • Acts as a resource server, enforcing access control and protecting resources.

    • Delegates authorization to an external authorization server, following best practices for secure, standards-based authentication and authorization flows.

    • Once the authorization request is successful, the server creates a session in the Trento API using a hardcoded username and password. This session is then used to interact with the Trento API on behalf of the authenticated user.

  • Container-Ready:

    • Includes a Dockerfile for easy containerization and deployment.

Quick Start

  1. git clone https://github.com/trento-project/mcp-server.git && cd mcp-server

  2. make run

  3. Install VS Code and the Copilot extension (see other alternatives here)

  4. Install the Trento MCP Server by clicking here

Getting Started

Go to the documentation for detailed information on how to set up, configure, and use the Trento MCP Server. We recommend starting with the VS Code integration guide to learn how to use it along with Visual Studio Code. Alternatively, you can refer to the SUSE AI integration guide to understand how to deploy and use this project with SUSE AI.

License

See the LICENSE notice.