- DIRECT
- CODE
- CONTEXT
- HUMAN
Short answer
How can I ask my AI questions about my documentation?
Your AI client uses the Fern MCP to scan your documentation domains and find specific technical answers. It pulls the exact details you need, from API endpoints to usage examples, without you having to search manually. You'll see how the AI handles these requests below.
The results.
What your AI delivers.
The AI turns raw documentation into direct answers.
DIRECT
Technical answers
The AI reads your docs to explain how a specific endpoint works or what parameters it requires.
CODE
Ready-to-use snippets
Your agent pulls correct code examples from your documentation to help you write implementation logic.
CONTEXT
API specifications
The AI identifies specific schema details and data types defined in your documentation domains.
HUMAN
Manual verification
If the documentation is missing a specific detail, the AI tells you it can't find it so you can check the source yourself.
The workflow
What your AI does when a question arrives.
The AI acts as a bridge between your chat interface and your technical docs.
Scan documentation
The AI looks through your connected Fern documentation domains to find relevant sections.
post_chat_completionExtract technical details
It pulls specific API paths, request bodies, or error codes from the text.
post_chat_completionGenerate code examples
The agent uses the documentation context to write code that matches your specific API structure.
post_chat_completionVerify information
The AI checks the retrieved content against your question to ensure the answer is grounded in your docs.
post_chat_completion
Try it
Copy these to start.
Use these prompts to begin interacting with your documentation.
Starting points
These are opening lines. Swap out the bracketed text for your actual API names or documentation paths.
Fern Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_VqEKputPZIEstF5UI8C28igkFzBgP67EyQDUBcP9/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Fern capabilities are ready to use.
{
"mcpServers": {
"fern-mcp": {
"url": "https://edge.vinkius.com/vk_preview_VqEKputPZIEstF5UI8C28igkFzBgP67EyQDUBcP9/mcp"
}
}
}Explain how the [API Name] authentication works based on the docs.
Show me a Python example for calling the [Endpoint Name] endpoint.
What are the required fields for the [Resource Name] object?
Find the error code in the documentation for when a [Specific Action] fails.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Fern once, then ask.
Just link your Fern account. Your credentials stay encrypted, and you can immediately start asking questions in your preferred AI client.
Connect Fern to your AIFAQ
How the task behaves
- 01
Can the AI change my documentation?
No. The AI only reads the documentation to provide answers. It cannot edit, delete, or add any content to your Fern domains.
- 02
Does the AI know about my private API keys?
No. The AI only accesses the documentation content provided through the MCP. It does not have access to your actual runtime credentials or secrets.
- 03
What if the answer isn't in the docs?
If the information isn't in the documentation domains you connected, the AI will tell you it doesn't know. It won't guess or make up API details.
- 04
Can I use this with Cursor or Claude?
Yes. Any MCP-compatible client like Claude, Cursor, or Windsurf can use this once you connect it.
- 05
Does it support multiple documentation domains?
Yes. The AI can query across all the documentation domains you have connected through Fern.
More questions about Fern? See everything the Fern Connector can do
Connect Fern to Claude, Cursor, ChatGPT & more
