惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

美团技术团队
J
Java Code Geeks
有赞技术团队
有赞技术团队
GbyAI
GbyAI
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园 - 叶小钗
阮一峰的网络日志
阮一峰的网络日志
Microsoft Security Blog
Microsoft Security Blog
IT之家
IT之家
G
Google Developers Blog
月光博客
月光博客
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
S
SegmentFault 最新的问题
博客园 - 三生石上(FineUI控件)
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
博客园 - Franky
腾讯CDC
V
Visual Studio Blog
博客园 - 【当耐特】
D
Docker
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Engineering at Meta
Engineering at Meta
L
LangChain Blog

Mintlify Blog

22 UX improvements to the web editor Introducing the Mintlify Help Center Starter Kit Introducing the collaborative editor built for teams and agents Workflows, rebuilt Is your documentation agent-ready? Mintlify raises $45M Series B led by Andreessen Horowitz and Salesforce Ventures 5 things you didn't know you could do in the Mintlify web editor The improved Mintlify CLI Docs on autopilot: From zero to self-maintaining with Mintlify The state of agent traffic in documentation (March 2026) How we built a virtual filesystem for our Assistant We Replaced Our Internal Wiki With a Slack Bot. You Should Too. 8 ways teams use Mintlify to keep docs updated automatically Documentation is your AI interface What three years of watching AI in production taught us Bridging two JSX runtimes: How we solved Astro's React children problem AI agents are shipping faster than anyone can document Knowledge management systems for technical teams Workflows: Automate documentation maintenance Mintlify acquires Helicone to redefine AI knowledge infrastructure Why more product managers are switching to Mintlify Auto-generating documentation sites from GitHub repos Your docs, your frontend, our content engine Take control of your documentation system Almost half your docs traffic is AI, time to understand the agent experience @mintlify for better docs, faster Mintlify for Enterprise Real llms.txt examples from leading tech companies (and what they got right) Mintlify + Claude Opus 4.6: Powering AI-native knowledge management Declaring Clankruptcy: An experiment in agent orchestration
How to use MCP servers to generate docs
Tiffany Chen · 2025-04-18 · via Mintlify Blog

AI tools have become great at reading documentation and pulling answers. For example, fast, contextual AI chat for docs is now a baseline expectation of users.

But with the rise of Model Context Protocol (MCP), we're closer than ever to something new: AI that can generate high-quality documentation content.

In this tutorial, we'll walk through how you can use MCP servers to generate new content, using a product requirements document (PRD).

How to use MCP servers to write your docs (with Mintlify + Windsurf)

A quick refresher: what is MCP?

MCP is a standard introduced by Anthropic that allows AI applications to talk to external tools and data sources.

  • MCP servers expose your data in a structured way that AI applications can query. They act as intermediaries, like APIs for LLMs
  • MCP clients (like Windsurf, Cursor, or Claude Desktop) act as the interface to pull context or data from those servers and using it to generate answers or actions

MCP servers act as a bridge between your product and AI tools that people rely on.

Because Mintlify auto-generates MCP servers for your documentation, your customers can instantly plug your product into AI tools.

The flow for AI documentation generation

Say you work at AppleDB and you're about to launch a new analytics feature.

You already have a PRD, but haven't yet created the customer-facing documentation.

Using MCP servers, you can:

  1. Pull your writing style and tone from existing docs
  2. Feed the PRD into an AI tool like Windsurf, Claude, or Cursor
  3. Iterate and chat with the AI tool until you're satisfied with the writing
  4. Format the output using Mintlify components
  5. Push your new docs into production!

Flow chart of how to set up MCP servers

Step 1: Install your own docs' MCP server

First, you'll want to install the MCP server for your own product docs, AppleDB. That way, the AI tool can pull your tone, structure, and terminology when writing new content.

Head to your Mintlify dashboard, grab the generated install command under the “MCP server” tab, and run it in your terminal.

npx @mintlify/mcp@latest add [x]

This automatically adds your docs server config to your local MCP client.

Step 2: Install the Mintlify MCP server

Next, you need to install the Mintlify MCP server to help the AI tool format your content in Mintlify components, such as cards, callouts, anchors, etc.

To install it, run this command in your terminal:

npx @mintlify/mcp@latest add mintlify

You'll see both servers (AppleDB and Mintlify) listed in your MCP client config.

Step 3: Ask AI to generate the doc

Now that both servers are installed, it's time to generate your doc. Start by pasting in the PRD for your new feature.

Then you can use AI to:

  1. Write a draft of a help doc using the style and tone of AppleDB
  2. Input more context and iterate until you're satisfied with the draft
  3. Format it using Mintlify components and markdown

The AI tool will automatically query both MCP servers, drawing style and context from AppleDB and component formatting from Mintlify.

Since the tool also has the context of your entire documentation, you can also chat with AI to iterate as much as you want.

For example, you can ask “Are there any redundancies in this page with my existing docs?” The AI tool will scan your entire documentation and flag any overlaps.

Step 4: Deploy with Mintlify

Once the doc is generated and properly formatted, just copy the markdown into your Mintlify deployment, whether in your local environment or web editor.

Now you can ship your new docs page!

How MCP changes the game for documentation generation

Before MCP, you could technically use AI to write your docs. You could manually copy content into ChatGPT, going back and forth to piece everything together. It could have worked, but it was a tedious, fragmented process.

With an MCP server connected to your docs, writing with AI becomes a true iterative chat experience. You can give real-time feedback, revise instantly, and never worry about hunting down context or pasting things in.

What's next

You can try out this flow today, as Mintlify auto-generates MCP servers for all customer documentation.

Content generation is just the beginning. Soon, we're making it possible to handle the entire documentation workflow from your preferred AI tool: scanning your docs, generating new content, and submitting the final pull request.

Want to learn more about Mintlify or our AI documentation roadmap? Get in touch with our team.