Developers

INLEVEL9 Letter developer guide

Last updated: 2026-08-23

INLEVEL9 Letter publishes its public content in machine-readable form alongside the website. There is no API key and no application process. Every public integration below is unauthenticated and public-content only.

There is no authenticated API. Members-only article text is never served through any of these paths; locked issues return exactly the excerpt an anonymous reader sees on the web.

INLEVEL9 Letter OpenAPI 3.1

The public read API is described by an OpenAPI 3.1 JSON document. Every operation has a unique operationId, a description, typed parameters, and typed response schemas. Operator, subscriber, billing, and delivery APIs are intentionally excluded.

OpenAPI specification: https://letter.inlevel9.com/openapi.json

curl "https://letter.inlevel9.com/api/search?q=AI&locale=en&limit=5"

Structured JSON errors

Public API failures use application/problem+json. Every response includes a stable code, a human-readable message, and an actionable resolution. Unknown /api/* routes use the same shape instead of an HTML error page.

{
  "code": "invalid_locale",
  "message": "locale must be one of ko, en, zh-CN.",
  "resolution": "Choose a locale listed in the OpenAPI parameter schema."
}

Markdown content negotiation (INLEVEL9 Letter)

Send Accept: text/markdown to any public page URL and you get Markdown instead of HTML. Every page in the sitemap negotiates — issues, the three edition home pages, the archive, topic and category indexes, and the about, contact, developer, privacy, and terms pages. Responses carry Content-Type: text/markdown; charset=utf-8 and Vary: Accept. Issue pages arrive with YAML frontmatter holding the canonical URL, publication date, and issue number. An Accept header that rules out both HTML and Markdown receives 406 Not Acceptable.

curl -H "Accept: text/markdown" https://letter.inlevel9.com/

INLEVEL9 Letter MCP server

A Model Context Protocol 2026-07-28 server is available over Streamable HTTP. Current clients use server/discover and per-request _meta; legacy initialize clients remain supported. Register the URL below in Claude, ChatGPT, or any MCP-capable client to call this newsletter as tools. No authentication is required.

Discovery document	https://letter.inlevel9.com/api/mcp-manifest
Endpoint (Streamable HTTP)	https://letter.inlevel9.com/.well-known/mcp

curl -X POST "https://letter.inlevel9.com/.well-known/mcp" \
  -H "Accept: application/json, text/event-stream" \
  -H "Content-Type: application/json" \
  -H "MCP-Protocol-Version: 2026-07-28" \
  -H "Mcp-Method: server/discover" \
  --data '{"jsonrpc":"2.0","id":1,"method":"server/discover","params":{"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28","io.modelcontextprotocol/clientCapabilities":{}}}}'

Available tools

`search_issues`	Full-text search across published INLEVEL9 Letter issues. Use when you need to find whether this newsletter has covered a specific company, technology, policy, or event.
`get_issue`	Return one issue as Markdown with its canonical URL, publication date, and issue number. Issues older than the free window return their public excerpt only.
`list_recent_issues`	The newest published issues, most recent first. Use to see what this newsletter covered lately.

INLEVEL9 Letter RSS feeds

Full feeds, one per edition, updated the moment an issue publishes.

https://letter.inlevel9.com/rss.xml — Korean
https://letter.inlevel9.com/en/rss.xml — English
https://letter.inlevel9.com/zh-cn/rss.xml — Simplified Chinese

INLEVEL9 Letter chat webhooks

Register an incoming-webhook URL from Slack, Discord, Teams, Google Chat, Mattermost, or Dooray and every new issue arrives in that channel with its title, summary, and link. No bot install, no permission review.

Agent instruction files

These state when to use this source, when not to, and how to cite it.

/llms.txt — Site guide and entry points by use case (llmstxt.org format)
/llms-full.txt — When to use, when not to, citation rules, and the tool contract
/sitemap-index.xml — Every indexable URL
/robots.txt — Crawl policy, including AI crawlers

Support

If an integration is not behaving, write to contact@inlevel9.com. Contact