Skip to content

Revamp MCP server page (SDKs) #607

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 27, 2025
Merged

Revamp MCP server page (SDKs) #607

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
51 changes: 7 additions & 44 deletions fern/products/sdks/overview/mcp-server/introduction.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,26 +1,17 @@
---
title: Model Context Protocol
title: MCP server for your API
description: Learn how to use the Model Context Protocol (MCP) to integrate AI capabilities with your Fern documentation
---

<Tip>
**Looking for Fern's own MCP server?** If you want to connect your AI client to Fern's MCP server for help with Ask Fern, Docs, and SDKs, see the [fern-mcp-server repository](https://github.com/fern-api/fern-mcp-server). This page describes how Fern can help you build an MCP server for your own API.
</Tip>
<Markdown src="/snippets/wip-callout.mdx" />

[Model Context Protocol (MCP)](https://modelcontextprotocol.io) is an open standard by Anthropic that streamlines how AI applications connect with external data sources and tools, enabling AI agents to directly use your product’s APIs.

A “Built with Fern” MCP server augments your existing TypeScript SDK with MCP capabilities and integrates seamlessly with popular AI-powered tools including Cursor, Claude Desktop, and Windsurf. You can find a full list of MCP clients [here](https://modelcontextprotocol.io/clients).

<Note>
The MCP generator is in development. Interested in offering an MCP server for your API? Reach out via Slack or [email protected].
</Note>
[Model Context Protocol (MCP)](https://modelcontextprotocol.io) is an open standard by Anthropic that enables AI applications to connect with external data sources and tools.

Fern can generate a production-ready MCP server that augments your existing SDK. Developers can then interact with your API directly through AI clients (like Claude Desktop, Cursor, and Windsurf).

## How it works

**Fern can build a production-ready MCP server on top of your existing TypeScript SDK.** We maintain the package in its own `git` repository, making it easy for your existing developer community to discover and contribute to the project. We can also automatically publish new versions of the package to `npm` for you.

End users of a “Built with Fern” MCP server can typically get started with a **single config**:
Fern generates an MCP server on top of your existing SDK and maintains it in its own repository. Developers can install your MCP server by adding a configuration snippet to their AI client:

```json
{
Expand All @@ -34,36 +25,8 @@ End users of a “Built with Fern” MCP server can typically get started with a

```

To learn more about Model Context Protocol (MCP) servers, check out the [MCP server docs](https://modelcontextprotocol.io/quickstart/server).

## Case study: Webflow

**We worked with Webflow to launch their [official MCP server](https://www.npmjs.com/package/webflow-mcp-server)** using the existing [Fern-generated TypeScript SDK](https://github.com/webflow/js-webflow-api).

Check out the [source code on GitHub](https://github.com/webflow/mcp-server) and read the announcement from Webflow’s CTO on X:

<blockquote class="twitter-tweet"><p lang="en" dir="ltr">🚢 We just launched our Webflow MCP server! Check out Allan’s thread to learn more, watch the demo video below, then give it a try here: <a href="https://t.co/T2K3OpJ6O8">https://t.co/T2K3OpJ6O8</a> <a href="https://t.co/bFUfC64pcf">https://t.co/bFUfC64pcf</a> <a href="https://t.co/oonYuyjHiT">pic.twitter.com/oonYuyjHiT</a></p>&mdash; Webflow (@webflow) <a href="https://twitter.com/webflow/status/1907465818088054843?ref_src=twsrc%5Etfw">April 2, 2025</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>

## Why "Built with Fern"?

There are a few advantages in partnering with Fern to build your MCP server:

- **Keep your MCP server in sync with your API** - our implementation augments your existing TypeScript SDK.
- **Integrate with Fern Docs and AI Chat** - give your users the ability to query your docs directly from inside of Cursor, Claude Desktop, and more.
- **For APIs at scale** - leverage our team’s expertise developing, testing, and deploying MCP servers for products with hundreds of API endpoints.
- **Thought partnership** - the AI ecosystem is changing fast and we’re here to navigate it together with you, from the latest techniques to the tools that power them.

## How else can Fern support my MCP server launch?

We can provide **ready-to-use social media assets** for announcing your MCP support:
## Example: Webflow

- LinkedIn post template
- X (Twitter) post template
- Email announcement template
- Social media graphics
Webflow launched their [official MCP server](https://www.npmjs.com/package/webflow-mcp-server) using their existing [Fern-generated TypeScript SDK](https://github.com/webflow/js-webflow-api). You can view the [source code on GitHub](https://github.com/webflow/mcp-server).

As well as all of the **detailed documentation** that you’ve come to expect from Fern:

- Getting started guide
- API reference
- Usage guidelines and best practices