What is Mermaid-MCP?

Mermaid-MCP is a Model Context Protocol (MCP) server that generates Mermaid flowcharts from text inputs. It’s designed to be used with AI clients like Claude and Cursor.

How does Mermaid-MCP work?

It receives text input (descriptions, Mermaid code, etc.), uses an LLM to understand the request, generates HTML/CSS, renders a diagram, and exports it as a PNG image.

What diagram types does it support?

Flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, pie charts, and user journey maps.

How do I install Mermaid-MCP?

Clone the repository, create a virtual environment, install dependencies using pip install -r requirements.txt, and start the server with python src/server.py.

How do I connect it to my MCP client?

Add a new server in your MCP client settings, pointing to http://localhost:5000 (or your configured port).

Can I customize the diagram style?

Yes, you can use pre-defined CSS templates or provide your own custom CSS.

What is Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how applications provide context to LLMs.

What is UBOS?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department.

Can I adjust the size and resolution of the exported PNG image?

Yes, the server offers options to adjust PNG resolution and quality.

Where can I find the project repository?

The project repository is located at https://github.com/yourusername/mermaid-mcp.git.

How can I contribute to the project?

Fork the repository, create a feature branch, commit your changes, push to your branch, and submit a pull request.