Use these docs with AI agents

Give coding agents and AI tools access to the Krun docs through llms.txt, Markdown pages and the docs MCP server.

The Krun docs are available in formats that coding agents and AI assistants can read directly.

llms.txt

An index of every page, with descriptions and links to Markdown versions:

https://docs.krun.ai/llms.txt

The full content of the docs in one file:

https://docs.krun.ai/llms-full.txt

Markdown pages

Add .md to any page URL to get it as Markdown, for example:

https://docs.krun.ai/quickstart.md

Each page also has a menu at the top to copy it as Markdown or open it in ChatGPT, Claude, Perplexity, Cursor or VS Code.

Docs MCP server

The Krun docs have a Model Context Protocol (MCP) server that lets AI tools search and read the docs while they work:

https://docs.krun.ai/mcp

Claude Code

claude mcp add --transport http krun-docs https://docs.krun.ai/mcp

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "krun-docs": {
      "url": "https://docs.krun.ai/mcp"
    }
  }
}

VS Code

Add to .vscode/mcp.json:

{
  "servers": {
    "krun-docs": {
      "type": "http",
      "url": "https://docs.krun.ai/mcp"
    }
  }
}

The docs MCP server only searches and reads documentation. It cannot call the Krun API or see your API keys.

OpenAPI specification

Agents that generate API clients can use the specification directly:

https://api.krun.ai/openapi.json

Tips for prompting agents

When you ask a coding agent to integrate Krun, point it at the docs and state the key facts:

Integrate the Krun API (docs: https://docs.krun.ai/llms.txt).
Use the Python SDK: pip install krun-ai, from krun import Krun.
Read the key from KRUN_API_KEY, server-side only.
Handle abstention: answer.choice is None when answer.abstain is True.
confidence is the top-1 minus top-2 margin, not the probability of being correct.