Cortex - Turn API specs into docs, SDKs, and MCP servers

by
Cortex is an open source API knowledge layer that turns OpenAPI, AsyncAPI, GraphQL, gRPC, and OpenRPC specs into interactive documentation, typed SDKs in 11 languages, and MCP servers for AI agents.

Add a comment

Replies

Best
Hey Product Hunt 👋 I’m Nick, and I built Cortex because being an engineer in the AI era means your APIs increasingly need to serve two very different users: developers and AI agents. But supporting both often means doing the same work twice. You build documentation and SDKs for developers, then create separate MCP tools and context for agents. Today, these pieces are usually maintained separately. They drift out of sync, create duplicate work, and leave AI agents trying to understand your API from incomplete or outdated context. Cortex makes your API contract the source of truth. Give it your OpenAPI, AsyncAPI, GraphQL, gRPC, or OpenRPC specs, plus Markdown, and Cortex generates: 📚 Interactive documentation for developers ⌨️ Typed SDKs across 11 languages 🤖 MCP servers with typed tools and grounded API context Everything is open source and MIT licensed. You can customize the templates, publish the SDKs wherever you want, and host the generated documentation yourself. The idea is simple: define your API once, then give every developer and every agent the interface they need to actually use it. Check out the open source repo at I would love feedback from teams building APIs, SDKs, developer tools, and agent integrations. What would make Cortex more useful in your workflow?

 Love the idea of keeping one source of truth for both developers and AI agents. Really smart approach 👏

 thank you!

 generating a both type of MCP and SDKs tools the same requirement is really interesting, it seems like a smart way to avoid maintaining distinict docs for developers and agent.

how much setup are needed to go from an existing OpenAPI spec to a eork on MCP server??

​love that its open source and MIT licensed. lock in with api tools is usually my biggest concern so this is refreshing.

 thanks! ensuring everything stays interoperable and open source is definitely a priority for the project

  Absolutely that interoperability + open-source approach is what makes Cortex especially interesting. Looking forward to seeing where the project goes

Looks another amazing product. Congrats & team! Thanks for sharing 🙌🏻

 Thanks so much, Hamza!

​how does this compare to tools like fern or stainless when it comes to SDK generation quality?

Great question! Cortex provides full type safety for all generated SDKs, including GraphQL. It supports 11 languages, such as C++ and C, and allows custom generator configurations for specific edge cases. Plus, it's open-source (MIT License), ensuring no vendor lock-in! :)

does cortex generate types for all 11 languages automatically or do we need custom templates for languages like rust and go?

Great question! It generates SDKs automatically for all 11 languages. You'd only need to use custom generators if you have specific requirements, such as adding a custom license into the SDK.

I would love to know how it performs with large and messy real world specifications.

That's a great point. We've already tested it with popular existing schemas, such as GitHub's GraphQL, to see how it generates SDKs, docs, and MCPs, and it worked flawlessly.

Regarding the auto-generation of SDKs for 11 programming languages, what is your approach to ensuring consistency with any changes to the original specification, auto-regeneration on every change or manual intervention?
BTW, Congratulations & on the launch of Cortex 🚀🎊

Thanks for the question! I added validation support on the CLI to ensure the SDKs and MCP stay perfectly in sync with any spec changes.

The SDK generation is that your own work or are you using the one from OpenAPI ? The C# generation from openapi is a a messy code bloat.

the idea of interactive API docs sounds sweet, for me, the way i'd use this is via mcp, being a SWE myself, and i find this solution useful personally, gonna try it out, thanks!

 Thanks! I'm glad you think the MCP approach is useful. Let me know how you find it when you try it out!

​11 languages? my team can barely maintain two definitely giving this a shot over the weekend!

haha :). Hope you find it helpful for your workflow once tested.

 yeh sure

12
Next