What are the prerequisites for running the server?
You need Node.js 18.0 or higher and Docker with Docker Compose.
@tohachan
基本情報
A comprehensive MCP server that bridges the gap between LLMs and diagram creation through three powerful, independent tools: intelligent format selection, format-specific instruction generation, and professional diagram rendering (using kroki server). Each tool can be used standa
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"diagram-bridge-mcp": {
"command": "node",
"args": [
"/path/to/diagram-bridge-mcp/dist/index.js"
],
"enabled": true
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
Diagram Bridge Mcp is an MCP server that bridges LLMs and diagram creation through three independent tools: intelligent format selection (help_choose_diagram), format-specific instruction generation (get_diagram_instructions), and professional diagram rendering via a local Kroki service. It supports formats including Mermaid, PlantUML, C4 Model, D2, GraphViz, BPMN, Structurizr, Excalidraw, and Vega-Lite. Designed for developers using MCP clients (e.g., Cursor) who need LLMs to produce diagrams without manual format or rendering decisions.
Install Node.js 18+, clone the repo, run npm install && npm run build, then start services with docker-compose up --build. Configure your MCP client to point to the built dist/index.js file. The server automatically provides three tools (help_choose_diagram, get_diagram_instructions, render_diagram) that can be used standalone or in sequence.
You need Node.js 18.0 or higher and Docker with Docker Compose.
By default, rendered diagrams are saved to `{project-root}/generated-diagrams/`. Advanced configuration is described in the configuration guide.
The server supports Mermaid, PlantUML, C4 Model, D2, GraphViz, BPMN, Structurizr, Excalidraw, and Vega-Lite.
No. Rendering uses a local Kroki service started via Docker Compose, so all processing happens locally.
Add a JSON entry to your MCP client configuration with `command: "node"` and `args: ["/path/to/dist/index.js"]` as shown in the README.

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

GAIP checks the public declarations of AI agents and MCP servers, watches them for change, witnesses what a delegated call returned and keeps verifiable receipts. Free, read-only, no account or API key. Every result sta

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.
コメント