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

# WeChat Channels (视频号) data for AI agents

> WeChat Channels (视频号) video search, detail and metrics, comments, account profiles and video lists, collections, live detail and transcripts through AgentKey.

WeChat Channels (视频号) is the short-video feed inside WeChat, reaching the
whole WeChat user base, and it is even more closed than the rest of the app:
videos only open inside WeChat and there is no web presence to index. Through
AgentKey your agent reads public Channels data the same way it reads everything
else — `find_tools`, `describe_tool`, `execute_tool` — with several providers
behind the scenes, so one route failing does not stop the task.

## What you can ask

* *"Find WeChat Channels videos about camping from the past week."*
* *"这个视频号最近发了什么视频？"*
* *"From the link I copied, pull this Channels video's title, metrics and comments."*
* *"Which Channels account is bound to this Official Account?"*
* *"Transcribe this Channels video."*
* *"Is this account live right now, and what did its recent lives look like?"*
* *"Search for Channels creators about home fitness."*
* *"帮我看看这个视频号的合集里有哪些视频"*

## What's covered

**Videos**

* Resolve a copied link, preview URL or short feed ID to the video; title; full
  detail, including a realtime variant that takes the link directly
* Interaction metrics for a video; a downloadable media URL; share-URL
  generation
* Keyword search with publish-time and sort controls; search within a single
  channel
* Conversion of an encrypted export ID from search results into a usable video
  identity

**Comments**

* First-level comments, paginated; replies under a comment

**Accounts**

* Account info, profile and stats
* The account's video feed; its collections (合集) and the videos in each
* Account search by name or keyword
* The Channels account bound to an Official Account; channel ID → finder
  username

**Live**

* Live detail and live history for an account

**Transcripts**

* Video transcription as a submit-then-fetch task

## How to use it

Pass the request in plain language and let the router pick the tool:

```text theme={null}
find_tools(q="WeChat Channels videos about camping from the past week")
find_tools(q="这个视频号最近发了什么视频")
find_tools(prefix="social/wechat_channels")   # browse everything for Channels
describe_tool("<returned Provider/Operation>")
execute_tool("<Provider/Operation>", { ...params })
```

Both English and Chinese phrasing work, and the platform's usual English and Chinese names all land here. Always `describe_tool` before executing —
parameters and per-call costs differ between providers, and several tools take
Channels' own identifiers (object ID, nonce ID, v2Name) that earlier calls
return.

> [!NOTE]
>
> **Building with code?** The same capability is available as fixed-contract
> [Scenario Methods](/api-reference/scenario/overview) with automatic provider
> failover:
> [`social.wechat_channels.post.search`](/api-reference/scenario/methods/social-wechat_channels-post-search),
> [`social.wechat_channels.user.posts`](/api-reference/scenario/methods/social-wechat_channels-user-posts),
> [`social.wechat_channels.user.search`](/api-reference/scenario/methods/social-wechat_channels-user-search).
> Video detail, comments, live and transcripts are available through the
> catalog tools above.

## FAQ

> **Do I need a WeChat account?**
>
> No. AgentKey holds the upstream access; your agent only needs your AgentKey
> subscription.

> **I only have a link copied from WeChat. Is that enough?**
>
> Yes. A copied video link, preview URL or short feed ID resolves to the
> video's basic info and identifiers, and from there the detail, metrics and
> comment tools take over.

> **How fresh is the data?**
>
> Every call goes to the platform at request time; the realtime detail route
> in particular reads the video as it stands right now. Nothing is served
> from a stale archive.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.