Unified API source workflow
Combine API definitions and Markdown in a configured project, with contract validation before generation.
Cortex Docs
Cortex Docs turns API specifications and Markdown into interactive documentation, typed SDKs, and MCP servers for developers and AI agents.
API documentation, SDKs, and MCP servers from one workflow
Cortex Docs is an open-source API tooling workflow for turning API specifications and Markdown into three developer-facing outputs: interactive documentation, typed SDKs, and MCP servers. Its configuration model brings multiple API surfaces into one project and validates the contract before generation.
The product is designed for teams that need both a human interface for exploring an API and an agent interface for AI-assisted integration. Generated documentation can be self-hosted, while templates and generated code can be adapted and published through infrastructure chosen by the user.
Core capabilities
Interactive API documentation
Produce searchable guides, interactive references, copy-ready examples, and a live request builder in a documentation site.
Multi-language SDK generation
Generate typed clients for TypeScript, Python, Go, Java, Kotlin, Ruby, PHP, C#, Rust, C++, and C, with authentication, timeouts, streaming, retries, and package metadata included in the site’s examples and feature claims.
MCP servers for agents
Map API operations to typed MCP tools and package specifications, SDK guidance, and project documentation alongside the server.
Open and deployable output
Use open templates and sparse overrides to adapt generated code, publish packages to your own registries, and run documentation wherever Node runs.
Practical use cases
API teams maintaining docs as code
Maintain API definitions and Markdown in a single configured project, validate the contract, and regenerate the documentation surface as the API changes.
Developer onboarding and integration
Give application developers searchable reference material, runnable request exploration, copy-ready examples, and typed clients for integrating with an API.
Multi-language client distribution
Offer clients in the conventions of their ecosystems, using generated packages for languages such as TypeScript, Python, Go, Java, Kotlin, Ruby, PHP, C#, Rust, C++, and C.
Agent-assisted API integration
Expose API operations as typed MCP tools with specifications and SDK guidance so AI agents can discover interfaces and produce more grounded integration code.
Teams that want control over generated output
Override templates, publish generated packages to internal or public registries, and host the documentation on infrastructure that supports Node.
Pros and Cons
Pros
- Open-source and MIT-licensed, with templates and generated output available for customization.
- Provides documentation, SDK, and MCP generation in one configured workflow.
- Supports a broad set of listed SDK languages, including TypeScript, Python, Go, Java, Kotlin, Ruby, PHP, C#, Rust, C++, and C.
- Includes agent-oriented context such as typed MCP tools, embedded API specifications, SDK guides, and project documentation.
- Supports self-hosted documentation and publishing generated packages to user-controlled registries.
Cons
- The site does not document pricing, hosted plans, setup requirements, or operational limits; the listed pricing URL returns a 404.
- The evidence does not specify the full set of supported input formats, deployment configurations, or collaboration features beyond the documented workflow and output options.
FAQ
What does Cortex Docs generate?
Cortex Docs takes API specifications and Markdown as project sources, then generates interactive documentation, typed SDKs, and MCP servers from a configured workflow.
What API sources can Cortex Docs use?
The site shows a cortex.config.yml workflow with OpenAPI and GraphQL sources. It also states that REST, realtime, GraphQL, gRPC, and JSON-RPC sources can be combined in one project, although the available source formats and setup requirements should be confirmed for a specific implementation.
Can the generated output be self-hosted or customized?
Generated documentation can be self-hosted, and generated output can be deployed wherever Node runs. The project also supports exporting and overriding templates, including publishing generated packages to your own registries.
How does Cortex Docs support AI agents?
The generated MCP server provides typed tools mapped from API operations, along with embedded specifications, SDK guides, and project documentation intended to give AI agents more context during integration.
Quick Facts
- Category
- Developer Tool
- Primary users
- Developers and AI agents
- Inputs
- API specifications and Markdown
- Outputs
- Interactive docs, typed SDKs, and MCP servers
- License
- MIT
- Source domain
- cortexdocs.dev
Cortex Docs Alternatives
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repos and verifies changes with compilers, debuggers, sanitizers, and tests.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads in Firecracker micro-VMs with private networking and SDK, CLI, or MCP control.
GitBot
GitBot is a local browser workspace for reusable coding bots powered by Claude Code, Codex, or OpenCode, with persistent threads and configurable permissions.
hob
hob is an independent workspace for coding agents, with local control over sessions, terminals, history, routing, and follow-up work.
Ably Chat
Ably Chat is a chat API platform for custom realtime chat apps, with rooms, typing indicators, presence, reactions, message updates and usage-based pricing.
Manta AI
Manta AI is an autonomous web app testing tool that maps app behavior, catches regressions, and generates tests from a URL, no scripts or selectors needed.