Skip to main content
How do I point my agent, IDE, or automation at Tavus’s documentation and HTTP APIs? This guide helps you pick the right artifact for your workflow.

​
Documentation bundle reference

ArtifactRoleURL
llms.txtCurated directory of doc URLs for selective fetchhttps://docs.tavus.io/llms.txt
llms-full.txtFull bundled text export for offline or bulk ingesthttps://docs.tavus.io/llms-full.txt
openapi.yamlHTTP API contract (paths, request/response schemas, security schemes)https://docs.tavus.io/openapi.yaml
skill.mdAgent-oriented capability summary (Agent Skills conventions)https://docs.tavus.io/skill.md
MCPHosted Model Context Protocol server: search plus fetch full pages from the indexed docs site (see Model Context Protocol)https://docs.tavus.io/mcp

​
When to use what

  • MCP: Interactive tools that need live search and current page retrieval against the indexed site.
  • llms-full.txt: Bulk or offline ingestion; snapshot of doc text (not a substitute for OpenAPI).
  • openapi.yaml: Source of truth for HTTP APIs (requests, responses, auth headers); agents should not invent endpoints that contradict it.
  • llms.txt / selective fetches: Discovery and pulling specific pages when you do not want the full bundle.
  • skill.md: Compact capability orientation for agents; still point to OpenAPI and deep docs for details.

​
Model Context Protocol (MCP)

An MCP endpoint is available for this documentation site. Configure clients that support HTTP transport with: 
{
  "url": "https://docs.tavus.io/mcp",
  "transport": "http"
}
Use MCP when the tool needs live search and retrieval against the current indexed documentation, not a frozen file export.