SocialToAIStart freeConsole
POST/v1/search"platform": "wechat"

WeChat Articles Search API

Find articles by keyword.

Search WeChat articles by keyword and get back text, author, likes and publish time, as JSON over HTTP or from your AI client over MCP. A call to the WeChat Articles Search API costs 12 credits ($0.024 to $0.04 depending on the pack), failed calls are free, and the response has the same format as every other call. Last tested 2026-11-05.

100 credits on sign-up, no card needed
12 creditsper call, ≈ $0.024–$0.04
Usually 20 itemsup to 30 per page, one page per call
100% succeeded20 real calls in the last 7 days, median 2.8 s, usually 20 items, data to 2026-11-05
2026-11-05last tested
1.1 KBsample response, 1 item

Last updated:

Need 100 items? Send limit: 100 and one call pages for you: at most 5 pages, 60 credits. It stops once it has them or the list ends; pages it does not use are not charged, and neither are pages that fail. Reading 1,000 items comes to about 600 credits, about $2.00.

Daily watch: tell your AI “watch this daily” and this call runs by itself every day, sending only what is new: at most 372 credits a month, about $1.24. How to set it up

What you get from the WeChat Articles Search API.
From a recorded answer.

A recorded call returned 20 items; here is the first, field by field. Names and text are removed from the sample; the numbers are as recorded.

20 real calls in the last 7 days, 100% succeeded, median 2.8 s, usually 20 items (data to 2026-11-05).

Lighter for your AI: the same recorded data (20 items) is about 14,013 tokens as the platform's raw JSON and about 6,170 as this interface returns it, 55% fewer (measured 2026-11-06). How it was measured

FieldIn the recorded answer
urlnull
formatvideo
titlenull
textremoved from the sample
published_at2026-10-15T06:55:50.000Z
author.idnull: WeChat Articles cannot give it
author.usernamenull: WeChat Articles cannot give it
author.nameremoved from the sample
author.verifiednull: WeChat Articles cannot give it
author.followersnull: WeChat Articles cannot give it
metrics.likes1
metrics.commentsnull: WeChat Articles cannot give it
metrics.sharesnull: WeChat Articles cannot give it
metrics.collects3
metrics.viewsnull: WeChat Articles cannot give it
metrics.repostsnull: WeChat Articles cannot give it
imagesnull: WeChat Articles cannot give it
hashtagsnull: WeChat Articles cannot give it
is_pinnednull: WeChat Articles cannot give it

12 credits a call (≈ $0.024–$0.04): about 250 calls for $10.

Easier with a ready-made tool: Brand buzz. How people feel about it on each platform, what comes up most, and the posts behind it.

WeChat Articles Search API: request and response

curl https://api.socialtoai.com/v1/search \  -H "Authorization: Bearer $SOCIALTOAI_API_KEY" \  -H "Idempotency-Key: $(uuidgen)" \  -H "Content-Type: application/json" \  -d '{    "platform": "wechat",    "query": "咖啡店开业"  }'
import osimport uuidimport requestsresponse = requests.post(    "https://api.socialtoai.com/v1/search",    headers={        "Authorization": f"Bearer {os.environ['SOCIALTOAI_API_KEY']}",        # A new key for each request; the same one again retries it without paying twice.        "Idempotency-Key": str(uuid.uuid4()),    },    json={        "platform": "wechat",        "query": "咖啡店开业",    },)print(response.json())
# Connected over MCP? Ask in plain words.Search WeChat Articles for articles about "咖啡店开业".# Your AI calls the search tool with:{  "platform": "wechat",  "query": "咖啡店开业"}
Change the requestThe code above follows.
value
sort
published_within
Sign in to run12 creditsOpens in the Playground with these parameters after you sign in. It never runs by itself.
200 OK1.1 KB12 credits
{  "platform": "wechat",  "status": "ok",  "items": [    {      "platform": "wechat",      "id": "…",      "ref": "…",      "approx": [],      "type": "content",      "url": null,      "format": "video",      "title": null,      "text": "…",      "published_at": "2026-10-15T06:55:50.000Z",      "author": {        "id": null,        "username": null,        "name": "…",        "verified": null,        "followers": null      },      "metrics": {        "likes": 1,        "comments": null,        "shares": null,        "collects": 3,        "views": null,        "reposts": null      },      "images": null,      "hashtags": null,      "is_pinned": null    }  ],  "unavailable": ["author.id", "author.username", "author.verified", "author.followers", "metrics.comments", "metrics.shares", "metrics.views", "metrics.reposts", "images", "hashtags", "is_pinned"],  "page": {    "has_more": true,    "cursor": "cur_…",    "cursor_expires_at": "2026-10-17T10:46:20.000Z"  },  "cost_credits": 12}
@…·
likes 1comments nullshares nullcollects 3views null

Names and text were removed from the sample; the numbers are as recorded.

Sample data1 of the 20 items recorded

WeChat Articles Search API parameters.
6 parameters, 2 required.

Send them as a JSON body with POST. Your key goes in the Authorization header, never in the URL.

NameTypeRequiredDefaultDescription
platformstringRequired—Always "wechat" on this page.
querystringRequired—Search terms
sortstringOptional"relevance"By relevance, by time published (newest first) or by how hot
"relevance""latest""popular"
published_withinstringOptional—Only those published in the last day, week or half year
"day""week""half_year"
typestringOptional—"user": accounts instead of posts (102 credits).
"user"
cursorstringOptional—Pass page.cursor from the last response to get the next page.

WeChat Articles Search API response fields.
What WeChat Articles cannot give is marked.

FieldTypeMeaning
items[].urlstringA link that opens the item.
items[].formatstringvideo, image, text or article.
items[].titlestringThe title.
items[].textstringThe body text or caption.
items[].published_atstringWhen it was published, ISO 8601 in UTC.
items[].author.idstringalways nullThe author's account ID.
items[].author.usernamestringalways nullThe author's handle.
items[].author.namestringThe author's display name.
items[].author.verifiedbooleanalways nullWhether the author is verified.
items[].author.followersintegeralways nullThe author's follower count.
items[].metrics.likesintegerLikes.
items[].metrics.commentsintegeralways nullComments.
items[].metrics.sharesintegeralways nullShares.
items[].metrics.collectsintegerSaves.
items[].metrics.viewsintegeralways nullViews or plays.
items[].metrics.repostsintegeralways nullReposts.
items[].imagesstring[]always nullImage addresses.
items[].hashtagsstring[]always nullHashtags, without the #.
items[].is_pinnedbooleanalways nullWhether the author pinned it.
nullFields WeChat Articles cannot give

Read null as “WeChat Articles did not give this”, not as zero. These are always null on this call:

  • author.idThe author's account ID.
  • author.usernameThe author's handle.
  • author.verifiedWhether the author is verified.
  • author.followersThe author's follower count.
  • metrics.commentsComments.
  • metrics.sharesShares.
  • metrics.viewsViews or plays.
  • metrics.repostsReposts.
  • imagesImage addresses.
  • hashtagsHashtags, without the #.
  • is_pinnedWhether the author pinned it.
Other values of this call

Send the parameter and the call returns something else:

type=useraccounts instead of posts102 credits

Compared with the Zhihu Search API, this call does not give author followers or comments.

Every item also has platform, id, ref, approx and type; the response around the items is the same on every call. Response format

WeChat Articles Search API: paging and billing.

One call returns a page of usually 20 items, up to 30 items. When page.has_more is true, send page.cursor back as cursor for the next page; each page costs 12 credits and a cursor works for 30 minutes.
A call that runs and finds nothing is a successful call: status is "empty", items is empty, and it costs 12 credits.

5 calls per second per key, 20 after a purchase; going over is not charged. Rate limits

A failed call costs 0 credits and is never retried on its own. Error codes

“Last tested” above is the last day a real call of this interface succeeded. Each call reads from the platform, and fetched_at in the answer is when it was read. The same request sent again with the same key within 5 minutes is a replay (replayed: true): 0 credits, and the answer as first read.

These numbers come from real calls only, worked out once a day, without our own accounts: a customer's same request on one day counts once, by how it last ended; something that does not exist or a wrong parameter is not a failure; an interface with fewer than 20 calls shows none.

Once connected over MCP, these questions use the WeChat Articles Search API.

  1. Search WeChat Articles for articles about "咖啡店开业".
    search {"platform":"wechat","query":"咖啡店开业"}
    12 credits
  2. Find WeChat Articles accounts about "咖啡".
    search {"platform":"wechat","query":"咖啡","type":"user"}
    102 credits

Give this to your AI.
Copy it into Claude or ChatGPT.

How to connect
Prompt
Use the SocialToAI MCP server (https://mcp.socialtoai.com/mcp) for this: Search WeChat Articles for articles about "咖啡店开业".Call the search tool with {"platform":"wechat","query":"咖啡店开业"}. Needed: query; optional: sort (relevance, latest, popular), published_within (day, week, half_year).For many items pass limit (limit=100 is at most 5 pages) and one call pages for you; each page costs 12 credits and unused pages are not charged.Before you start, work out how many credits it will take in all and ask me; call it only after I agree.If SocialToAI is not connected yet, tell me how to connect it; never ask me to paste a key into the chat.Answer with a link to every item you used, and tell me how many credits it cost.

Paste it into a chat once SocialToAI is connected over MCP. There is no key in it: Claude and ChatGPT sign in, other clients send a key in a header.

These ready-made tools call it when they run.

brand-buzz
Brand buzz

How people feel about it on each platform, what comes up most, and the posts behind it

The same call on other platforms.

All platforms and prices
POST/v1/search{ "platform": "wechat", "query": "咖啡店开业" }12 creditsper call
Change one word in the request: platform. The response keeps the same shape.

Read next.

WeChat Articles official API: access, prices and limits

What its own API allows, who can use it and what it costs, with sources.

How to let AI read WeChat Official Account articles

let your AI read WeChat Official Account articles

Turn WeChat Official Account articles into RSS, or push them to Feishu and WeCom

turn WeChat Official Account articles into a private RSS feed, or push them to Feishu and WeCom

Can Claude read WeChat Official Account articles?

what Claude can and cannot read on WeChat Official Account articles, with sources and a real request

Can ChatGPT read WeChat Official Account articles?

what ChatGPT can and cannot read on WeChat Official Account articles, with sources and a real request

WeChat Articles MCP server

Let your AI read WeChat Articles.

WeChat Articles Search API: questions.
Short answers.

All WeChat Articles data APIs
Do I need a WeChat Articles account or WeChat Articles's own API access?
No. You only need a SocialToAI key. The call returns content and account information publicly visible on WeChat Articles; you never sign in to WeChat Articles or apply for anything there.
Can I get accounts instead of posts?
Yes: send type=user in the request. That call costs 102 credits.
What does one call cost in dollars?
12 credits: $0.04 at 300 credits per dollar (purchases from $10), $0.024 at 500 per dollar (from $200). Credits never expire and there is no subscription. 100 free credits on sign-up, no card.
Am I charged when a call fails or finds nothing?
A failed call costs 0 credits and is never retried on its own. A call that runs and finds nothing is a successful call: status is "empty" and it costs 12 credits.
How much does one call return?
One call returns a page of usually 20 items, up to 30 items. When page.has_more is true, send page.cursor back as cursor for the next page; each page costs 12 credits and a cursor works for 30 minutes.
Is there a rate limit?
5 calls a second per key, 20 a second after your first purchase. A request over the limit is told how long to wait and is not charged.
How do I use it from Claude, ChatGPT or Cursor?
Yes. In Claude or ChatGPT, add the MCP address https://mcp.socialtoai.com/mcp as a custom connector, sign in with the code we email you and press Allow; there is no key to paste. In Claude Code, run one command, type /mcp, pick socialtoai and sign in; Codex and Cursor sign in too, with their steps on the connect page. Then ask in plain words and your AI calls search for you.
Start free · 100 credits

Your AI is one URL away
from all of social media.

100 credits on sign-up, no card needed