fern-api/fern-mcp-server
If you are the rightful owner of fern-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The Model Context Protocol (MCP) server is a framework designed to facilitate communication between different components of a machine learning model ecosystem, enabling seamless integration and interaction.
fern-mcp-server
Connect AI clients like Claude, Windsurf, and Cursor to the Fern MCP server for help with Fern's AI search (Ask Fern), documentation platform, and SDK generation.
Once configured, your AI client uses the ask_fern_ai
command to query Fern's knowledge base, enabling contextual assistance with Fern's tools directly in your development environment.
Note: These instructions assume you already have an MCP-compatible AI client installed (Claude Desktop, Cursor, Windsurf, etc.).
To get started with the Fern MCP server:
-
Clone this repository and navigate into the
fern-mcp-server
directory. -
Install dependencies and start the development server:
npm install npm start
-
Add the MCP server configuration to your AI client's config file. The location of this file depends on which AI client you're using and your operating system.
More information on the exact location of this file and how to access or create it:
-
Add the following to your MCP config file:
{ "mcpServers": { "fern": { "command": "node", "args": ["<PATH_TO_PROJECT>/fern-mcp-server/dist/index.js"] } } }
Replace
PATH_TO_PROJECT
with your local path to thefern-mcp-server
project. -
After saving the configuration file, restart your AI client. Once you restart, you can test the connection by asking questions like "What MCP servers are available?" or "Can you help me with Fern documentation?"