mermaid-mcp
Renders Mermaid diagram markup (flowcharts, sequence, class, ER, gantt, state diagrams) to PNG images, with options for theme, background color, width, height, and scale.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mermaid-mcprender a sequence diagram for API authentication"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mermaid-mcp
An MCP server that renders Mermaid
diagram markup to PNG images, using @mermaid-js/mermaid-cli
(Puppeteer/Chromium) under the hood.
Give it AI-generated Mermaid — flowcharts, sequence, class, ER, gantt, state diagrams — and get back a rendered image, returned inline so the host can preview it and/or written to a file on disk.
Tool
render_mermaid
Parameter | Type | Required | Description |
| string | yes | Mermaid diagram source, e.g. |
| string | no | Absolute path ending in |
| enum | no |
|
| string | no | e.g. |
| number | no | Output width in pixels |
| number | no | Output height in pixels |
| number | no | Device scale factor; higher = sharper/larger PNG (default |
Returns a short text summary plus the PNG as inline MCP image content. When outputPath is
supplied, the file is written there and the path is included in the summary.
Related MCP server: Mermaid SVG MCP Server
Install & build
npm install
npx puppeteer browsers install chrome # download the headless Chromium used for rendering
npm run buildRendering runs a headless Chromium via Puppeteer. If npm install doesn't fetch it automatically,
run npx puppeteer browsers install chrome (as above). It lands in Puppeteer's cache
(~/.cache/puppeteer / %USERPROFILE%\.cache\puppeteer). On Windows, if extraction stalls, delete
the partial chrome/win64-* folder and re-run the install.
Test
npm testIntegration tests using Node's built-in test runner (node:test). They exercise the renderer
(input validation, inline render, render-to-file) and a full MCP stdio round-trip (spawn the server,
list tools, call render_mermaid). The render tests launch headless Chromium, so they need the
Chromium install above and take a few seconds each.
Configure in an MCP client
After npm run build, point your MCP client at the built entry over stdio.
Claude Code
# From a local build:
claude mcp add mermaid -- node /absolute/path/to/mermaid-mcp/dist/index.js
# Or from the published package:
claude mcp add mermaid -- npx -y @volare-consulting/mermaid-mcpClaude Desktop / generic mcpServers config
{
"mcpServers": {
"mermaid": {
"command": "node",
"args": ["/absolute/path/to/mermaid-mcp/dist/index.js"]
}
}
}Development
npm run dev # run the server from TypeScript source via tsxReleasing
Published to the public npm registry as
@volare-consulting/mermaid-mcp
via a tag-driven GitHub Actions release (.github/workflows/publish.yml), which calls the org's
shared publish-npm-public reusable workflow.
Bump
versioninpackage.jsonon a PR and merge tomain.Tag the merge commit and push the tag:
git tag v0.1.0 && git push origin v0.1.0
The tag must equal the package.json version or the job fails. Pushing a v* tag builds and
publishes the package (tests are skipped — they need headless Chromium the publish runner doesn't
provide). Authentication uses the org-level NPM_TOKEN secret.
License
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Volare-Consulting-Software/mermaid-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server