Mcp Dingtalk Doc
@hykfft
About Mcp Dingtalk Doc
No overview available yet
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"dingtalk-doc": {
"command": "python3",
"args": [
"~/Documents/AIGC/dingtalk_api/mcp_dingtalk_doc/server.py"
],
"env": {
"DINGTALK_COOKIE": "你的Cookie",
"DINGTALK_DOC_OUTPUT_DIR": "~/Documents/cursor-mcp/dingDoc"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Mcp Dingtalk Doc?
Mcp Dingtalk Doc is an MCP server that parses DingTalk document content and generates styled HTML output. It is intended for users who need to extract and view DingTalk documents programmatically. The server was tested on macOS only.
How to use Mcp Dingtalk Doc?
Install from source with pip install -e . or via uv, set the DINGTALK_COOKIE environment variable, then run server.py. Configure the server in any MCP‑compatible client (e.g., Cursor). Two tools are exposed: parse_document (saves files) and get_html (returns HTML without saving). Provide a DingTalk document URL or node ID as input.
Key features of Mcp Dingtalk Doc
- Full GET → extract dentryKey → POST → HTML pipeline
- Supports paragraphs, tables, images, and code blocks
- Beautiful rendering with gradient UI and dark code theme
- One‑click copy for code blocks
- Accepts full URL or NODE_ID as input
- Auto‑archives output in per‑node folders
Use cases of Mcp Dingtalk Doc
- Analyze a DingTalk document and generate a local HTML copy
- Embed DingTalk document content into other tools via MCP
- Perform quick document inspection without manual navigation
- Archive documents with structured JSON data and rendered HTML
FAQ from Mcp Dingtalk Doc
What are the runtime requirements?
Python 3.10 or higher is required. The server was tested on macOS.
How do I obtain the DingTalk cookie?
Open a DingTalk document in a browser, press F12, go to the Network tab, refresh the page, and copy the Cookie field from any request.
What files does parse_document produce?
It creates a folder containing four files: {NODE_ID}_mainsite.json, {NODE_ID}_document.json, {NODE_ID}_content.json, and {NODE_ID}.html.
What are known limitations?
OSS‑encrypted document content is not fully decrypted. Some elements (lists, blockquotes, etc.) are not yet supported. The cookie must be renewed when the session expires.
Which transport does the server use?
It uses the standard MCP protocol with stdio transport, invoked via python3 server.py.
Frequently asked questions
What are the runtime requirements?
Python 3.10 or higher is required. The server was tested on macOS.
How do I obtain the DingTalk cookie?
Open a DingTalk document in a browser, press F12, go to the Network tab, refresh the page, and copy the `Cookie` field from any request.
What files does `parse_document` produce?
It creates a folder containing four files: `{NODE_ID}_mainsite.json`, `{NODE_ID}_document.json`, `{NODE_ID}_content.json`, and `{NODE_ID}.html`.
What are known limitations?
OSS‑encrypted document content is not fully decrypted. Some elements (lists, blockquotes, etc.) are not yet supported. The cookie must be renewed when the session expires.
Which transport does the server use?
It uses the standard MCP protocol with stdio transport, invoked via `python3 server.py`.
Basic information
More Other MCP servers
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Nginx UI
0xJackyYet another WebUI for Nginx
Website
FunnyWolfAdversary simulation and Red teaming platform with AI
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Comments