M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
M

Mermaid MCP Server

Community
Generate Mermaid diagrams and charts dynamically with AI via MCP.
How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #290 of 438
Stars
★ 642 Popular
Transport
stdio (local process) · SSE · Streamable HTTP
Runtime
Node.js · Docker · Hosted (no local runtime)
Credentials
No credential needed
License
MIT
Last commit
Tools
1
47FMRS · D

mcp-mermaid is a practical MCP server with multiple transports, easy installation, and rich features. Suitable for developers wanting to integrate AI-based diagram generation, but input validation and privacy considerations are recommended.

Strongest · Setup experience 13/20 Weakest · Reliability 7/20

Reliability
7/20
Security and permissions
7/20
Maintenance
10/20
Documentation
10/20
Setup experience
13/20
Why each score
Reliability 7/20
Only the README and repo metadata are available; no server manifest, source code, or tests were supplied. The README claims stdio/SSE/streamable support and multiple output formats, but lists no concrete tool names/parameters and provides no evidence of error handling or dependency control. The happy path is plausible, but with no verifiable execution evidence the static calibration cap applies and a conservative score is given.
Security and permissions 7/20
No malware or credential issues are apparent, but the README explicitly supports generating public mermaid.ink URLs (svg_url/png_url), meaning user diagram content may be sent to a third-party external service without confirmation of external requests; with source code unavailable, other network or file side effects cannot be ruled out. Main risks are visible, but permission boundaries, confirmation, and data-flow disclosure are incomplete.
Maintenance 10/20
An MIT license, a clear owner, an npm version badge, and a build badge indicate activity. However, the supplied evidence contains no commit history, release timeline, dependency update record, or security response channel, and the open issue count alone does not demonstrate responsiveness. This matches the 'active but governance/versioning gaps' 10-point anchor.
Documentation 10/20
The README covers Mac/Windows installation, Docker, SSE/Streamable access points, CLI options, development steps, and output formats, making it usable. But it lacks tool-level parameter details (tool names, input schemas), limits (size/rate/cost), troubleshooting, error-message guidance, and layered documentation. There are hidden assumptions and troubleshooting gaps.
Setup experience 13/20
The README provides ready-to-use client config JSON for mainstream clients (Claude, VSCode, Cline, Cherry Studio) plus npx, global install, Docker, and HTTP/SSE transport options, with Mac/Windows coverage and clear steps. However, since this is a static review without executable tests or CI verification, out-of-the-box behavior cannot be fully confirmed, so the score is kept below the 15 static cap.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

  • Developers needing AI assistance to produce technical documentation diagrams (e.g., architecture, flow).
  • Teams looking to integrate diagram generation into automated workflows.
  • AI users of desktop apps like Claude, VSCode, Cline, etc.

Not for

  • Batch generation of static diagrams (better use Mermaid CLI or libraries directly).
  • Scenarios requiring custom rendering beyond Mermaid's capabilities.
  • Users without Node.js or npm access.

Required permissions

  • Network access: Required if using remote Mermaid API or exporting URLs.
  • File system: Can write PNG files in the server directory when output type is 'file'.
  • Local ports: If using SSE or Streamable, needs to listen on local ports.

Risks and side effects

  • Mermaid syntax from user input could be malicious; filter inputs as needed.
  • Misconfiguration may overwrite or create unintended files.
  • Remote URL mode creates public links, potentially exposing diagram content; be mindful of privacy.

Setup

Before you start

Runtime：Node.js · Docker · Hosted (no local runtime)

  1. Ensure Node.js and npm are installed.
  2. Add the server configuration to your MCP client (e.g., Claude Desktop) as shown above.
  3. Restart the client and start using.
claude_desktop_config.json 
{
  "mcpServers": {
    "mcp-mermaid": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-mermaid"
      ]
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "mcp-mermaid": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-mermaid"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add mcp-mermaid -- npx -y mcp-mermaid

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

The generate_mermaid tool should appear in the client's tool list; ask it to render a simple flowchart and return an svg or URL — successful rendering confirms the connection.

Troubleshooting

  1. Ensure npx is available and Node.js is up-to-date.
  2. Check MCP client configuration, especially the command and arguments.
  3. For SSE/Streamable, check port availability and firewall rules.
  4. Inspect service logs or use MCP Inspector for debugging.
  5. Verify network connectivity to remote APIs or URLs.

Things to try

Once connected, you can ask your AI assistant things like:

  • Draw a mermaid flowchart of a user login process and export it as a PNG file
  • Generate a sequence diagram for order status and give me a shareable svg_url
  • Create a dark-themed gantt chart with a light gray background, output as base64
  • Make a class diagram showing inheritance between Animal, Dog, and Cat

Tools 1

generate_mermaid writes
Generates a Mermaid diagram based on user input, with options for type, theme, background color, and output format.

Use cases

Generate flowcharts, sequence diagrams, Gantt charts, etc., directly in AI conversations.
Save AI-generated diagrams as PNG files or share via URLs.
Quickly create visual diagrams in MCP-capable IDEs or chat tools.

Supported clients

Claude Desktop

Listed from the project's documentation, not tested by this site.

Overview

mcp-mermaid is an MCP server that enables AI models to generate Mermaid diagrams and charts dynamically. It fully supports all Mermaid features and allows configuration of background color and theme. It supports exporting to base64, SVG, Mermaid source, local files, and remote URLs, with Mermaid validation to aid multi-round output of correct syntax.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 62.9k · Tools 2 Compare with this →
Compare with other MCP servers

Source revision 13497062a980 Data synced 2026-10-12 Read the FMRS scoring method