todiagram-mcp-windows-fix
Windows-compatible MCP server for ToDiagram that fixes ERR_UNSUPPORTED_ESM_URL_SCHEME on Node.js v22+ on Windows, enabling AI assistants to generate diagrams via ToDiagram.
README
todiagram-mcp-windows-fix
Windows-compatible fork of @todiagram/todiagram-mcp that fixes ERR_UNSUPPORTED_ESM_URL_SCHEME on Node.js v22+ and v25+ on Windows.
Connect ToDiagram to Cursor, Claude, Windsurf, and other AI assistants — now works on Windows!
⚠️ The Problem
The original @todiagram/todiagram-mcp crashes on Windows with:
Fatal error in main(): Error [ERR_UNSUPPORTED_ESM_URL_SCHEME]:
Only URLs with a scheme in: file, data, and node are supported by the default ESM loader.
On Windows, absolute paths must be valid file:// URLs. Received protocol 'c:'
Root cause: In dist/mcp-server.js, the lazyLoadUtil() function dynamically imports tool modules using path.join(), which on Windows produces paths like C:\Users\...\tools\file.js. The Node.js ESM loader requires file:// URLs, not bare Windows paths.
✅ The Fix
A one-line change in dist/mcp-server.js:
- import { fileURLToPath } from "url";
+ import { fileURLToPath, pathToFileURL } from "url";
// ... in lazyLoadUtil():
- await import(toolPath);
+ await import(pathToFileURL(toolPath).href);
pathToFileURL() converts C:\Users\...\file.js → file:///C:/Users/.../file.js, which the ESM loader accepts on all platforms.
📦 Install
npm install -g todiagram-mcp-windows-fix
🔧 MCP Configuration
Claude Code (.mcp.json)
{
"mcpServers": {
"todiagram": {
"type": "stdio",
"command": "todiagram",
"env": {
"TODIAGRAM_API_KEY": "your-api-key-here"
}
}
}
}
Or via npx
{
"mcpServers": {
"todiagram": {
"type": "stdio",
"command": "npx",
"args": ["-y", "todiagram-mcp-windows-fix"],
"env": {
"TODIAGRAM_API_KEY": "your-api-key-here"
}
}
}
}
API Key Setup
- Go to ToDiagram Editor
- Click the account icon at top right
- Go to API Key section
- Create a key with a descriptive name and expiry time
🐛 Upstream Issue
This fix should be applied to the original @todiagram/todiagram-mcp package. The upstream issue is in src/mcp-server.ts:
// Current (broken on Windows):
for (const toolPath of toolsPaths) {
await import(toolPath);
}
// Fix:
import { pathToFileURL } from "url";
for (const toolPath of toolsPaths) {
await import(pathToFileURL(toolPath).href);
}
Affected platforms: Windows with Node.js v22+ (any version using ESM loader with strict URL scheme validation)
Affected versions: @todiagram/todiagram-mcp v1.1.0 and likely earlier versions
✅ Platform Compatibility
| Platform | Node.js v20 | Node.js v22 | Node.js v25 |
|---|---|---|---|
| Windows | ✅ | ✅ | ✅ |
| macOS | ✅ | ✅ | ✅ |
| Linux | ✅ | ✅ | ✅ |
📄 License
FSL-1.1-ALv2 (same as upstream)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.