langchain-ai/mcpdoc

• highreadme#1

  Reposition README's opening to clarify purpose and audience

  原因：

  当前

  # MCP LLMS-TXT Documentation Server
  
  ## Overview
  
  llms.txt is a website index for LLMs, providing background information, guidance, and links to detailed markdown files. IDEs like Cursor and Windsurf or apps like Claude Code/Desktop can use `llms.txt` to retrieve context for tasks. However, these apps use different built-in tools to read and process files like `llms.txt`. The retrieval process can be opaque, and there is not always a way to audit the tool calls or the context returned.
  
  MCP offers a way for developers to have *full control* over tools used by these applications. Here, we create an open source MCP server to provide MCP host applications (e.g., Cursor, Windsurf, Claude Code/Desktop) with (1) a user-defined list of `llms.txt` files and (2) a simple `fetch_docs` tool read URLs within any of the provided `llms.txt` files. This allows the user to audit each tool call as well as the context returned.

  复制粘贴的修复

  复制

  # MCP LLMS-TXT Documentation Server: Custom, Auditable Context for LLM-Integrated IDEs
  
  This open-source server enables developers to serve user-defined `llms.txt` documentation files directly to LLM-integrated development environments (IDEs) and applications like Cursor, Windsurf, and Claude Code/Desktop. It provides full control and auditability over the documentation context retrieved by AI assistants, addressing the opacity of built-in retrieval tools.

  待办完成忽略
• mediumtopics#2

  Add more specific topics to improve categorization

  原因：

  当前

  agents, claude-code, cursor, ide, llms, llms-txt

  复制粘贴的修复

  复制

  agents, claude-code, cursor, ide, llms, llms-txt, documentation-server, custom-docs, llm-context, auditability, developer-tools

  待办完成忽略
• mediumabout#3

  Refine the repository description for clarity

  原因：

  当前

  Expose llms-txt to IDEs for development

  复制粘贴的修复

  复制

  An open-source server to provide custom, auditable llms.txt documentation context to LLM-integrated IDEs like Cursor and Claude Code.

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  How can I audit documentation retrieval by AI coding assistants in my IDE?

  你：未被推荐
  AI 推荐顺序：

  1. GitHub Copilot
  2. Codeium
  3. Tabnine
  4. Jedi (davidhalter/jedi)
  5. Dash
  6. Zeal (zealdocs/zeal)
  7. Browser Developer Tools
  8. VS Code (microsoft/vscode)
  9. PyCharm
  10. IntelliJ
  11. Sublime Text
  12. Notepad++ (notepad-plus-plus/notepad-plus-plus)
  13. Obsidian
  14. Notion

  AI 推荐了 14 个替代方案，却始终没点名 langchain-ai/mcpdoc。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  Tool to serve custom technical documentation to LLM-integrated development environments?

  你：未被推荐
  AI 推荐顺序：

  1. Read the Docs
  2. Docusaurus
  3. MkDocs
  4. GitBook
  5. Sphinx
  6. Next.js
  7. Nuxt.js

  AI 推荐了 7 个替代方案，却始终没点名 langchain-ai/mcpdoc。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  warn

  建议：

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of langchain-ai/mcpdoc?

  pass
  ⚠AI 未点名 langchain-ai/mcpdoc —— 很可能在说另一个项目

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts langchain-ai/mcpdoc in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 langchain-ai/mcpdoc

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo langchain-ai/mcpdoc solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 langchain-ai/mcpdoc

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？