Developers

MOTS-c API & developer portal

The MOTS-c API is a public, read-only interface to every medically reviewed page on this site. It is built for AI agents and applications: content is available as structured JSON and as clean Markdown, described by an OpenAPI 3.1 specification, and exposed as native tools through a Model Context Protocol server.

No authentication or API key is required. All endpoints are read-only, cacheable, and CORS-enabled, so you can call them from a browser, a server, or an LLM function-calling runtime.

Base URL

https://motsc.com/api/v1

Endpoints

GET/api/v1/pagesoperationId: listPages

List every content page with its URL, type, title, and description. Filter with ?type=article.

GET/api/v1/pages/{path}operationId: getPage

Fetch one page as Markdown by path, e.g. /api/v1/pages/dosage. Use listPages to discover valid paths.

GET/api/v1/search?q=operationId: searchContent

Keyword search across articles and topic pages.

Quickstart

Search for content, then read a page as Markdown:

# List every page (discover valid paths)
curl "https://motsc.com/api/v1/pages"

# Search
curl "https://motsc.com/api/v1/search?q=insulin%20resistance"

# Read a page as Markdown (use a path from listPages)
curl "https://motsc.com/api/v1/pages/dosage"

Errors are returned as structured JSON with a stable code, a human-readable message, and a resolution hint.

OpenAPI specification

The full API is described by a self-documenting OpenAPI 3.1 document. Every operation has a unique operationId, typed parameters, and referenced response schemas, so it works directly with LLM function-calling and code generators.

https://motsc.com/openapi.json

MCP server

A Model Context Protocol server exposes the same content as callable tools (list_pages, search_content, get_page) over Streamable HTTP. Claude, ChatGPT, and other MCP-capable agents can connect natively.

Endpoint:  https://motsc.com/api/mcp
Discovery: https://motsc.com/.well-known/mcp
Transport: streamable-http

Markdown & llms.txt

Any page is available as Markdown: send an Accept: text/markdown header, or append .md to the path. The llms.txt index lists every page and developer resource for agents.

curl -H "Accept: text/markdown" https://motsc.com/dosage
curl https://motsc.com/dosage.md