{
"markdown": "# ![](\"https://mermaid.js.org/favicon.svg\")
MCP Mermaid  [](https://github.com/hustcc/mcp-mermaid/actions/workflows/build.yml) [](https://www.npmjs.com/package/mcp-mermaid) [](https://smithery.ai/server/@hustcc/mcp-mermaid) [](https://www.npmjs.com/package/mcp-mermaid) [](https://archestra.ai/mcp-catalog/hustcc__mcp-mermaid)\n\nGenerate [mermaid](https://mermaid.js.org/) diagram and chart with AI MCP dynamically. Also you can use:\n\n- ![](\"https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*ZFK8SrovcqgAAAAAAAAAAAAAemJ7AQ/original\")
[mcp-server-chart](https://github.com/antvis/mcp-server-chart) to generate chart, graph, map.\n- ![](\"https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*EdkXSojOxqsAAAAAQHAAAAgAemJ7AQ/original\")
[Infographic](https://github.com/antvis/Infographic) to generate infographic, such as `Timeline`, `Comparison`, `List`, `Process` and so on.\n- 🖼️ [figure.ling.pub/gallery](https://figure.ling.pub/gallery) to browse and share AI-generated diagrams and figures created with mcp-mermaid and other tools.\n\n\n## ✨ Features\n\n- Fully support all features and syntax of `Mermaid`.\n- Support configuration of `backgroundColor` and `theme`, enabling large AI models to output rich style configurations.\n\n- Support exporting to `base64`, `svg`, `mermaid`, `file`, and remote-friendly `svg_url`, `png_url` formats, with validation for `Mermaid` to facilitate the model's multi-round output of correct syntax and graphics. Use `outputType: \"file\"` to automatically save PNG diagrams to disk for AI agents, or the URL modes to share diagrams through public mermaid.ink links.\n\n\n![\"mcp-mermaid\"](\"https://mermaid.js.org/header.png\")
\n\n\n## 🤖 Usage\n\nTo use with `Desktop APP`, such as Claude, VSCode, Cline, Cherry Studio, and so on, add the MCP server config below. On Mac system:\n\n```json\n{\n \"mcpServers\": {\n \"mcp-mermaid\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"mcp-mermaid\"\n ]\n }\n }\n}\n```\n\nOn Window system:\n\n```json\n{\n \"mcpServers\": {\n \"mcp-mermaid\": {\n \"command\": \"cmd\",\n \"args\": [\n \"/c\",\n \"npx\",\n \"-y\",\n \"mcp-mermaid\"\n ]\n }\n }\n}\n```\n\nAlso, you can use it on aliyun, modelscope, glama.ai, smithery.ai or others with HTTP, SSE Protocol.\n\n**Access Points:**\n- SSE: `http://localhost:3033/sse`\n- Streamable: `http://localhost:1122/mcp`\n\n**Available Docker Tags:**\n- `susuperli/mcp-mermaid:latest` - Latest stable version\n- View all available tags at [Docker Hub](https://hub.docker.com/repository/docker/susuperli/mcp-mermaid/tags)\n\n\n## 🚰 Run with SSE or Streamable transport\n\n### Option 1: Global Installation\n\nInstall the package globally:\n\n```bash\nnpm install -g mcp-mermaid\n```\n\nRun the server with your preferred transport option:\n\n```bash\n# For SSE transport (default endpoint: /sse)\nmcp-mermaid -t sse\n\n# For Streamable transport with custom endpoint\nmcp-mermaid -t streamable\n```\n\n### Option 2: Local Development\n\nIf you're working with the source code locally:\n\n```bash\n# Clone and setup\ngit clone https://github.com/hustcc/mcp-mermaid.git\ncd mcp-mermaid\nnpm install\nnpm run build\n\n# Run with npm scripts\nnpm run start:sse # SSE transport on port 3033\nnpm run start:streamable # Streamable transport on port 1122\n```\n\n### Access Points\n\nThen you can access the server at:\n\n- SSE transport: `http://localhost:3033/sse`\n- Streamable transport: `http://localhost:1122/mcp` (local) or `http://localhost:3033/mcp` (global)\n\n## 🎮 CLI Options\n\nYou can also use the following CLI options when running the MCP server. Command options by run cli with `-h`.\n\n```plain\nMCP Mermaid CLI\n\nOptions:\n --transport, -t Specify the transport protocol: \"stdio\", \"sse\", or \"streamable\" (default: \"stdio\")\n --port, -p Specify the port for SSE or streamable transport (default: 3033)\n --endpoint, -e Specify the endpoint for the transport:\n - For SSE: default is \"/sse\"\n - For streamable: default is \"/mcp\"\n --help, -h Show this help message\n```\n\n## 🔨 Development\n\nInstall dependencies:\n\n```bash\nnpm install\n```\n\nBuild the server:\n\n```bash\nnpm run build\n```\n\n### Start the MCP server\n\n**Using MCP Inspector (for debugging):**\n\n```bash\nnpm run start\n```\n\n**Using different transport protocols:**\n\n```bash\n# SSE transport (Server-Sent Events)\nnpm run start:sse\n\n# Streamable HTTP transport\nnpm run start:streamable\n```\n\n**Direct node commands:**\n\n```bash\n# SSE transport on port 3033\nnode build/index.js --transport sse --port 3033\n\n# Streamable HTTP transport on port 1122\nnode build/index.js --transport streamable --port 1122\n\n# STDIO transport (for MCP client integration)\nnode build/index.js --transport stdio\n```\n\n## 🐳 Docker Usage\n\nRun MCP Mermaid with Docker:\n\n```bash\n# Pull the image\ndocker pull susuperli/mcp-mermaid:latest\n\n# Run with SSE transport (default)\ndocker run -p 3033:3033 susuperli/mcp-mermaid:latest --transport sse\n\n# Run with streamable transport\ndocker run -p 1122:1122 susuperli/mcp-mermaid:latest --transport streamable --port 1122\n```\n\n## 📄 License\n\nMIT@[hustcc](https://github.com/hustcc).\n",
"bytes": 5631,
"sha": "5fbc1da9dab174156aa46f602a312f7670c854801f2916bf01ac62e4db950400",
"repo_slug": "hustcc/mcp-mermaid",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/mcp_ai_smithery_hustcc_mcp_mermaid_d8c89862/readme"
}