Design, art and accessibility · MCP server
Mermaid MCP: MCP server, setup and security
Mermaid MCP is an MCP server published on GitHub that lets an AI agent generate Mermaid diagrams and export them in multiple file formats. Its repository has 53 stars and its last commit is from November 5, 2025, but it declares no licence.
| Adoption (stars) | 17/40 | |
|---|---|---|
| Maintenance | 10/30 | |
| Framework (licence, registry, official) | 5/30 |
What Mermaid MCP does
According to its repository: “Mermaid diagram generation (flowcharts, sequence, class, ER, architecture and state diagrams) with templates, layout engines and SVG/PNG/PDF export.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Mermaid MCP is listed under Design, art and accessibility, a category of 95 servers in the directory, where it ranks #46 by stars.
Topics declared by the repository: architecture, automation, claude, cli-tool, copilot, devtools.
Installing and connecting Mermaid MCP
No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: TypeScript. Listed systems: macOS, Windows, Linux.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
Points found for Mermaid MCP:
- No licence: without a licence the code is not legally reusable, even if it is public. Avoid it in a company setting without the author's agreement.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on October 30, 2025, the Narasimhaponnada/mermaid-mcp repository has 53 stars and 10 forks, with 3 open issues. It has more stars than 53% of the servers in the directory. Last change 12 months ago.
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Mermaid MCP is still a modest project: read its code and compare it with the alternatives before using it.
Limitations
- No commit for 12 months
- No licence declared
- Install from source
Avoid if…
- Company use without the author's agreement
Alternatives
- Pascal 3D Editor25.1K ★
- Next AI Draw.io36.4K ★
- Measure1.4K ★
- TerraVision1.7K ★
- Davinci resolve MCP3.7K ★
- MeiGen AI Design MCP1.8K ★
Learn more
Frequently asked questions
How do I install Mermaid MCP?
No package is declared in the MCP registry: clone the Narasimhaponnada/mermaid-mcp repository, follow its README, then declare the start command in your client's MCP configuration.
Is Mermaid MCP free?
The code is public but has no declared licence: it is not formally free to reuse.
Is Mermaid MCP safe?
Points to watch: no licence. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by Narasimhaponnada on GitHub. Check who maintains it before giving it access.
What are the alternatives to Mermaid MCP?
In the same category: Pascal 3D Editor, Next AI Draw.io, Measure, and TerraVision. Pascal 3D Editor and Next AI Draw.io score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score