> ## Documentation Index
> Fetch the complete documentation index at: https://docs.video2ctx.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Use video2ctx from agents

> Give an agent source-linked video context through the current REST API.

Agents can call the same hosted REST endpoints as any server application. A reliable integration separates discovery, selective retrieval, and evidence presentation.

<Steps>
  <Step title="Discover narrowly">Search for videos or resolve the relevant resource in your own application before requesting deeper datasets.</Step>
  <Step title="Fetch only needed context">Retrieve metadata first, then transcript, comments, channel information, or playlist items according to the task.</Step>
  <Step title="Preserve provenance">Keep video IDs, source URLs, transcript timestamps, fetch times, partial flags, and warnings with the text given to the model.</Step>
  <Step title="Return verifiable evidence">Link claims back to the video and timestamp instead of treating model output as the source.</Step>
</Steps>

Use a server-side tool wrapper so the API key never enters a model prompt or browser bundle. Bound query length, response size, continuation depth, and the number of fresh operations an agent can initiate.

<Warning>
  video2ctx does not currently publish a dedicated Agent API, hosted MCP server, or installable agent skill. Those names describe future product directions, not available contracts.
</Warning>