What are the runtime requirements for Ilograph MCP Server?
Python 3.10 or higher is required. Docker is optional for containerized deployment.
@QuincyMillerDev
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ilograph-mcp-server": {
"command": "docker",
"args": [
"build",
"-t",
"ilograph-mcp-server",
"."
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Ilograph MCP Server is an MCP‑compliant server that automatically analyzes source code in Python, JavaScript/TypeScript, and Java to generate native .ilograph diagram files. It can optionally render diagrams as SVG, PNG, HTML, or PDF via the Ilograph Export API. The server is designed for developers and architects who want to produce architecture diagrams from existing codebases and integrate them with AI‑assisted tools.
Install via pip (pip install -e .) or Docker, then start the server with python -m src.main serve. Use the CLI command python -m src.main analyze /path/to/project to scan a codebase and produce an .ilograph file. The server exposes six MCP tools (e.g., analyze_codebase, generate_diagram, render_diagram) that can be invoked by AI assistants like JetBrains AI Assistant or GitHub Copilot.
Python 3.10 or higher is required. Docker is optional for containerized deployment.
An Ilograph API key is required only for rendering diagrams (SVG, PNG, HTML, PDF) via the Ilograph Export API. Analysis and .ilograph file generation work without a key.
The server can analyze Python, JavaScript, TypeScript, and Java codebases.
You can run it directly with Python and pip, or use the provided Dockerfile and Docker Compose configuration for containerized deployment. Kubernetes manifests are also included.
The server communicates over HTTP (default port 8000) and exposes a health check endpoint. API‑key authentication is optional and used only for the Ilograph Export API rendering features.
Open-source MCP to use Blender with any LLM

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
🚀 The fast, Pythonic way to build MCP servers and clients.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
评论