How do I get my AI to read what Xiaohongshu (RedNote) says about a topic?
Connect SocialToAI to your AI client over MCP, then ask in plain words. In this recorded run an AI client answered “What are people on Xiaohongshu saying about camping coffee?” with 1 request on Xiaohongshu: 13 items read in 7.6 seconds for 36 credits ($0.12). Below are the calls it made, the answer with its sources, and the prompt and API calls to run it yourself. Recorded 2026-10-18.
The question
What are people on Xiaohongshu saying about camping coffee?
The notes are in Chinese and spread over many searches, and a search shows notes one by one, not which aspect comes up most. Your AI reads the Chinese and answers in the language you asked in. Reading what this run returned by hand takes about 2 minutes (7 words at 240 a minute; 763 Chinese characters at 400 a minute).
What the AI did
It chose the tools itself: 1 request on Xiaohongshu. Each row is one tool call as the client showed it, with what it sent, how much came back and what it cost.
| Platform | Tool | Sent | Requests | Returned | Credits |
|---|---|---|---|---|---|
| Xiaohongshu | brand_buzz | brand: "露营咖啡" · about: "户外露营时自己做咖啡" · platforms: ["xiaohongshu"] · window: "90d" · scale: "small" | 1 | 13 notes | 36 |
| Total | 1 | 13 items | 36 | ||
The answer
What the client answered, from what it had read. The line under each finding is a post it read, or a figure from those posts.
8 of the 13 posts found are about it: 100% positive, 0% neutral, 0% negative. What they mention most:
- Features38%“泰摩手冲套装，户外也能稳定萃取”3 notes
- Ease of use25%“意外比想象中方便。 撕开直接倒进水或牛奶里，冷水大约3秒就能化开”2 notes
- Quality13%“亲手萃取的温柔质感 是成年人超治愈的低成本快乐”1 note
The posts it rests on
A selection of what was read; the marked words are what a finding rests on. An item without a link says so.
- Xiaohongshu · note4dFinding 1
泰摩手冲套装，户外也能稳定萃取： ▫️C6手摇磨豆机，全金属机身，握感舒适
Open the source - Xiaohongshu · note13wFinding 3
按下城市生活暂停键▶️ 山野、微风、手冲咖啡 亲手萃取的温柔质感 是成年人超治愈的低成本快乐 #逃离城市 #户外放空
Open the source - Xiaohongshu · note11wFinding 1
Omnicup便携式电动咖啡机，露营必备好物。#打杯咖啡野餐去 #露营咖啡手册 #户外咖啡 #带上咖啡去旅行
Open the source - Xiaohongshu · note11wFinding 2
这次露营带了几颗咖啡液，意外比想象中方便。 撕开直接倒进水或牛奶里，冷水大约3秒就能化开，不用烧水，也不用带一堆咖啡器具
Open the source
What it cost
1 request, 36 credits in total: $0.12 at the $10 rate. Every answer of the API states the credits it charged and the balance left, so your AI can tell you what a question cost. A call that fails costs nothing.
| Pack | Credits per dollar | This answer |
|---|---|---|
| $10 = 3,000 credits | 300 | $0.12 |
| $50 = 20,000 credits | 400 | $0.09 |
| $200 = 100,000 credits | 500 | $0.072 |
Ask it yourself
Connect SocialToAI to your AI client once (the steps for each client), then paste the question. You do not name tools or parameters: the client picks them.
What are people on Xiaohongshu saying about camping coffee?The same in code: the calls this run made, as requests to the API.
curl https://api.socialtoai.com/v1/tools/brand_buzz \ -H "Authorization: Bearer $SOCIALTOAI_KEY" \ -H "Content-Type: application/json" \ -d '{ "brand": "露营咖啡", "about": "户外露营时自己做咖啡", "platforms": ["xiaohongshu"], "window": "90d", "scale": "small" }'What to try next
- Ask next: “Which gear comes up most?”
- Ask next: “Compare with last quarter”
- Change the topic, and ask for the answer in English or in Chinese.
- Ask for the notes behind each point, with links, and read them yourself.
- Run it as one request with the ready-made tool Brand buzz: What people say about a brand or product on each platform: the share of each attitude, what is mentioned most, and the posts with the most engagement, each with its source link.
Last updated: