Fern Connector for AI agents.
6 live capabilities
Manage documentation platforms and trigger website indexing for AI search.
Waiting for input…
Why people use Fern
Fern for managing documentation indexing and AI search
With this Connector, you just tell your agent to index the new site. It handles the request to Fern and keeps your documentation ready for users instantly. You get a faster workflow where the documentation platform actually responds to your commands.
What Vinkius changes
You get a direct way to manage your documentation platform's backend through a simple chat interface.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Updating documentation for a new release
A documentation engineer tells their agent to use index_website on a new URL so the AI search results update immediately.
- Real-world use case 02
Granting secure API access
A developer asks the agent to generate a JWT using get_jwt so they can provide a teammate with temporary access.
- Real-world use case 03
Troubleshooting user search issues
A support lead asks their agent to show recent queries using get_recent_queries to see why users are hitting dead ends.
Complete set · 6capabilities
The complete Fern capability set.
These are the exact actions your AI can choose when you ask it to work with Fern.
01—03
3 capabilities in this set.
Part of 6 available through Fern.
- 01 Capability
Get jwt
Generate a JWT from your Fern API key for secure access.
- 02 Capability
Get recent queries
Pull recent user queries and analytics to see how people interact with your docs.
- 03 Capability
Get search key
Get Algolia search credentials for your documentation platform.
04—06
3 capabilities in this set.
Part of 6 available through Fern.
- 04 Capability
Index website
Start a new crawling and indexing job for a specific website.
- 05 Capability
Post chat completion
Talk to the Ask Fern AI assistant to get answers from your specific documentation domains.
- 06 Capability
Whoami
Get the current user's information to verify authentication status.
Set up in minutes
One URL. Then ask Fern to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Fern from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_VqEKputPZIEstF5UI8C28igkFzBgP67EyQDUBcP9/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Fern, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Fern for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_VqEKputPZIEstF5UI8C28igkFzBgP67EyQDUBcP9/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Fern URL.
- Step 03
Save and start
Save the connection and enable Fern in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"fern": {
"url": "https://edge.vinkius.com/vk_preview_VqEKputPZIEstF5UI8C28igkFzBgP67EyQDUBcP9/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Fern
Open Agent mode in chat and ask: "Using Fern, help me...". 6 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"fern": {
"url": "https://edge.vinkius.com/vk_preview_VqEKputPZIEstF5UI8C28igkFzBgP67EyQDUBcP9/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Fern
Ask Copilot: "Using Fern, help me...". 6 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"fern": {
"url": "https://edge.vinkius.com/vk_preview_VqEKputPZIEstF5UI8C28igkFzBgP67EyQDUBcP9/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Fern
Open Cascade and ask: "Using Fern, help me...". 6 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"fern": {
"url": "https://edge.vinkius.com/vk_preview_VqEKputPZIEstF5UI8C28igkFzBgP67EyQDUBcP9/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Fern
Ask Cline: "Using Fern, help me...". 6 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add fern --transport http "https://edge.vinkius.com/vk_preview_VqEKputPZIEstF5UI8C28igkFzBgP67EyQDUBcP9/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Fern
Ask Claude: "Using Fern, show me...". 6 tools are ready
Where the request belongs
Work Fern can move forward.
This is for the documentation engineer who's tired of manually triggering crawls every day, the support lead who needs to know what users are searching for, and the dev who needs to manage API access keys without hunting through a dashboard.
Documentation Engineer
Automates indexing jobs and monitors search trends to ensure docs stay fresh.
Support Team Lead
Uses the Ask Fern assistant to quickly find answers for complex customer questions.
Developer
Manages secure documentation access keys and verifies user permissions programmatically.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsSwiftype
Connect your AI to Elastic Swiftype. Query your search engines, manage documents, and retrieve deep analytical insights natively from the terminal.
Lucidworks Fusion (AI Search & Discovery)
Manage AI-powered search via Lucidworks Fusion. execute semantic queries, index documents, and monitor ML training jobs.
Archbee
Manage documentation spaces, sync OpenAPI specs, and organize technical knowledge directly from your AI agent.
Glean
Search across all your company apps and docs with AI that understands your organization and surfaces the right answer instantly.
AddSearch
Equip your AI agent with AddSearch to query your indexed site content, push new documents, and retrieve search analytics instantly.
Obsidian Publish
Empower your AI to read your public or private Obsidian Publish sites. Index files, crawl navigation trees, and retrieve deep markdown knowledge.
Bring your own AI
Change the model, client or framework. Keep Fern connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Fern.
The practical details behind the request, access and result.
Can I use the Fern MCP to update my AI search results?
Yes, you can use the Connector to trigger new indexing jobs. This ensures that your AI-ready documentation stays current whenever you push new content.
How does the Fern MCP help with documentation analytics?
It lets your agent pull recent user queries directly. You can see what your audience is actually looking for without leaving your chat interface.
Can the Fern MCP help me manage my documentation access keys?
Yes, it can generate JWTs and search keys on demand. This makes it much easier to manage secure access for your team or users.
Is the Fern MCP good for testing my documentation's AI assistant?
It's great for that. You can use it to send questions to the Ask Fern assistant to see how it handles specific queries from your domains.
Who should use the Fern MCP for their documentation?
It's built for documentation engineers, support teams, and developers. Anyone who needs to manage the backend of a Fern-hosted documentation platform will find it useful.
Can I use the AI assistant to query my documentation?
Yes, use the post_chat_completion capability with your documentation domain and a list of messages. The agent will interact with the Ask Fern assistant to provide relevant answers.
How do I update the search index for a new site?
Use the index_website capability by providing the documentation domain and the base URL you want to crawl. This will trigger a new indexing job for the Ask Fern assistant.
How can I see what my users are searching for?
The get_recent_queries capability allows you to retrieve analytics and recent questions asked by users on a specific documentation domain.
One connection away
Give your agent a direct line to Fern.
Connect Fern once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available