Model Context Protocol integration
We added this functionality in a patch. To use Model Context Protocol (MCP) with Tosca, you need to install patch 1 or later.
Model Context Protocol (MCP) is an open standard that connects AI assistants to external systems. With the Tosca MCP Server, AI assistants can access your Tosca workspace and help you create, organize, update, use, and run test assets.
Components
The Tosca MCP integration consists of these components:
|
Component |
Description |
|---|---|
|
AI assistant |
Your own AI assistant that you provide and configure. The assistant sends requests to the Tosca MCP Server and displays the results. |
|
Tosca MCP Server |
An add-in that acts as the bridge between Tosca and your AI assistant. It communicates with the AI assistant through an HTTP connection and provides access to Tosca's capabilities. |
|
Tosca |
The source of all testing data and capabilities. |
Supported AI assistants
We've tried the Tosca MCP Server with the following AI assistants:
-
Claude Code and Claude Desktop
-
Cursor AI
-
Visual Studio Code
Feel free to experiment with other AI assistants—provided that the assistant supports MCP—but we can't guarantee results.
Workflow
Your basic MCP workflow is quite minimal:
Additional resources
For the best results, we recommend that you use the Tosca MCP Server together with the skills we've created. You can download these skills from this Tricentis GitHub repository (opens in new tab).
We also recommend that you explore these third-party resources for further guidance (all links open in new tab):
-
Model Context Protocol main site is a good starting point if you're new to MCP. Learn about MCP architecture, how to set up your own environment, and how to debug and troubleshoot MCP Servers. For example, our own developers are big fans of MCP Inspector.
-
Claude Code docs, Claude Desktop docs, Cursor AI docs, Visual Studio Code docs. Learn how to configure your own AI assistant, integrate it with MCP, and troubleshoot common issues.