Mantine provides LLM-friendly documentation to help AI tools like Cursor , Windsurf , GitHub Copilot , ChatGPT , and Claude understand and work with the Mantine UI library.
llms.txt documentation is updated with every Mantine release.
The LLM documentation includes:
In Cursor, you can reference the documentation using the @Docs feature:
When using ChatGPT or Claude:
While Copilot doesn't directly support external documentation, you can:
Mantine also provides skills for AI coding agents in the mantinedev/skills repository.
Currently available skills:
Install each skill from the repository:
In your AI prompt, explicitly tell the agent to use one of the installed skills.
If your agent does not support $skill-name mentions, reference the skill name in plain text and ask the agent to follow it.
Mantine also provides an MCP server package:
The server reads Mantine static MCP data published on mantine.dev and exposes tools that AI agents can call directly:
Most MCP-compatible tools support adding servers with a JSON configuration. Use this server definition:
To use a different data source (for example, alpha docs or local static files), add env variables:
If the client supports custom MCP servers, add the same command and args:
Then use prompts like:
Here are some example prompts you can use with AI tools:
The LLM documentation is automatically generated from our source files using a compilation script. It includes:
There are two generated formats:
To ensure you have the latest documentation, we regenerate these files with each release. The files follow the LLMs.txt standard for better compatibility with AI tools.
If you find any issues with the LLM documentation or have suggestions for improvement, please open an issue on our GitHub repository.