mcp-mermaidjs-server
An MCP server for working with MermaidJS, using `mmdc`.
Documentation
tech.unravel/mcp-mermaidjs-server
An MCP server for working with MermaidJS, using `mmdc`.
We create two simple tools:
- save-diagram
- visualize-diagram
Using these tools, a host can create beautiful mermaid-js diagrams by:
- creating an mmd spec and saving it
- then rendering the saved-spec using specific output format and (optionally) CSS (via access to `mmdc`)
Usage
Building the Uberjar
1. `make clean && make build`
Running the MCP server
PRE-REQUISITES: Needs mmdc CLI to be installed.
Some example commands you can try in Claude Desktop or Inspector:
1. Create a MermaidJS Sequence Diagram from this spec:
sequenceDiagram
%% See https://mermaidjs.github.io/sequenceDiagram.html
loop everyday D-2 working days 16:00
ABCD->>DEE: [14:25] BEE (Calculation per TC until ACK becomes OK)
ABCD->>FGG: BEE (Calculation per TC until ACK becomes OK)
Note over ABCD,FGG: D-2 weekdays at 14:25
ABCD->>HII: Projected Authorisations to HII
Note over ABCD,HII: D-2 weekdays at 16:00
end
loop D-1 before deadline at 7:45
HII->>DEE: Submission
Note over HII,DEE: D-1 before deadline
HII->>FGG: Submission
Note over HII,FGG: D-1 before deadline
endBefore running the MCP server
Remember:
1. Replace the full-path to the `tech.unravel/mcp-mermaidjs-server` Jar with the correct path on your system (i.e. replace `/Users/vedang/repo-name` below with the correct path)
2. Specify the full-path to `mmdc` on your system
In Claude Desktop
"mcp_mermaidjs_server": {
"command": "java",
"args": [
"-Dclojure.tools.logging.factory=clojure.tools.logging.impl/log4j2-factory",
"-Dorg.eclipse.jetty.util.log.class=org.eclipse.jetty.util.log.Slf4jLog",
"-Dlog4j2.contextSelector=org.apache.logging.log4j.core.async.AsyncLoggerContextSelector",
"-Dlog4j2.configurationFile=log4j2-mcp.xml",
"-Dbabashka.json.provider=metosin/jsonista",
"-Dlogging.level=INFO",
"-Dmcp.vegalite.mmdc_executable=/Users/vedang/.local/share/nvm/v23.11.0/bin/mmdc",
"-cp",
"/Users/vedang/repo-name/target/tech.unravel/mcp-mermaidjs-server-1.0.0.jar",
"tech.unravel.mcp-mermaidjs-server"
]
}In MCP Inspector
Remember to use the full-path to the `tech.unravel/mcp-mermaidjs-server` JAR on your system.
npx @modelcontextprotocol/inspector java -Dclojure.tools.logging.factory=clojure.tools.logging.impl/log4j2-factory -Dorg.eclipse.jetty.util.log.class=org.eclipse.jetty.util.log.Slf4jLog -Dlog4j2.contextSelector=org.apache.logging.log4j.core.async.AsyncLoggerContextSelector -Dlog4j2.configurationFile=log4j2-mcp.xml -Dbabashka.json.provider=metosin/jsonista -Dlogging.level=INFO -Dmcp.vegalite.mmdc_executable=/Users/vedang/.local/share/nvm/v23.11.0/bin/mmdc -cp /Users/vedang/repo-name/target/tech.unravel/mcp-mermaidjs-server-1.0.0.jar tech.unravel.mcp-mermaidjs-serverLicense
Copyright © 2025 Unravel.tech Engineering
Distributed under the MIT License
Frequently asked questions
What is mcp-mermaidjs-server?
mcp-mermaidjs-server is An MCP server for working with MermaidJS, using `mmdc`.
How do I install mcp-mermaidjs-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-mermaidjs-server open source?
Yes — it is hosted on GitHub at https://github.com/unravel-team/mcp-mermaidjs-server.
Related MCP tools
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-gra...
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Built for the Model Context Protocol to enhance AI capabilities.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP