With new AI agents and the Model Context Protocol (MCP), CANoe executes complete workflows via prompts: turning requirements into validated tests in minutes
Stuttgart, August 20, 2026 – Vector is expanding its CANoe development and testing environment with new AI and MCP capabilities. Users can now describe development, analysis, and testing tasks by entering a prompt in natural-language. Specialized AI agents will derive the corresponding steps or complete workflows from these instructions and execute them automatically. The underlying language model is provided by the users themselves, such as the LLM behind GitHub Copilot or Claude. Vector supplies the open AI layer consisting of agents, skills, and MCP tools that can be extended with own components and domain-specific knowledge.The MCP Server integrated into CANoe and the CANoe AI Package are now available in Version 20 SP2. From a single prompt, an AI agent creates the appropriate CAPL test from a requirement, executes the test in CANoe, analyzes errors, corrects the CAPL code, and reruns the test. The agent then hands the scenario to the user, who validates the results via the synchronized CANoe windows and approves the results. Tasks that previously took hours or days can now be completed in a matter of minutes. Users determine how autonomously the agents operate. Every step remains transparent and can be monitored live within the development environment and in CANoe.
The CANoe AI Package is based on an open ecosystem of AI agents that utilize skills and MCP tools. With prompts, users can read and customize configurations, control simulations, create tests, analyze communication flows, as well as generate and optimize CAPL, C#, and Python code. Through Vector-RAG (retrieval-augmented generation), agents can access a knowledge base containing relevant information from the Vector documentation. As a result, responses are based on verified expert knowledge rather than assumptions generated by the language model. New users gain quick access to CANoe, while experienced users can integrate automated workflows into their environments – ranging from simple queries to fully orchestrated processes.
The CANoe AI Package is available to download for free from the Vector website. It is compatible with CANoe 20 SP2 and later versions and requires a language model provided by the user.
More information: www.vector.com/canoe-ai
Picture: CANoe becomes an AI-powered engineering assistant for development, testing, and analysis Image rights: Vector Informatik GmbH
