How does QwenWork get Xiaohongshu, Douyin and WeChat data? Add one connector (2026)
4 fields and it reads them: in the QwenWork desktop app, 扩展 → 连接器 on the left → + 添加 → 手动填写配置, server type Streamable HTTP, address https://api.dataxapi.com/mcp, header Authorization set to Bearer and your key; a page of Xiaohongshu note search at $0.0200. The free trial covers up to 333 calls; a failed call is not charged.
Updated 2026-11-14
What goes in the connector?
Or choose 粘贴 JSON 配置 and put the same under mcpServers, with type streamable-http. Then turn it on under 已安装 and expand it to see the tools.
| Field | Value |
|---|---|
| Server type | Streamable HTTP |
| Server name | dataxapi |
| Server address | https://api.dataxapi.com/mcp |
| Headers | Authorization: Bearer, a space, then your API key |
Then what?
Ask it to list DataXAPI's tools first: 5, at no cost; a 401 means the key or its Bearer is wrong. Then ask, for instance “use DataXAPI to find the most-saved Xiaohongshu notes on coffee, then read the comments on the top 5”.
Once connected it has 5 tools: find names the endpoint for a need and describe gives its parameters and price, both free; call fetches a page of data and is charged per call; read_more reads what was cut and account shows the balance, also free.
The key sits in the client and the AI decides how many calls to make, so give that key a daily and monthly spending limit; a failed call is not charged, and every call is in the console's call log, marked MCP.
Why DataXAPI
- Steady: endpoints were available 99.9% of the last 30 days, on a public status page you can check.
- Fast: a paid call took 2.5 seconds at the median over the last 7 days (counted 2026-11-06).
- Fewer tokens: across 226 endpoints, one recorded real response each, the platform's own JSON comes to 9.2M tokens and what an AI reads through DataXAPI's MCP server to 452k, 95% fewer; the JSON of a direct API call is 90% fewer too (counted 2026-11-06). Every platform answers in one shape: the author in
author, counts inmetrics, the next page inpage.next_cursor, so another platform needs no new parser. - See before you pay: every endpoint's page shows a recorded real response, field by field.
- Spending you control: a failed call is not charged; each key can have a limit,
X-Max-Pricecaps one call, and the sameIdempotency-Keywithin 24 hours is never charged twice. - Ready for AI: a remote MCP server listed in the official MCP registry as
com.dataxapi/mcp, usable from Claude, Cursor and ChatGPT. - Free trial of up to 333 calls, no card.
Endpoints
Each with its price; every page has the parameters, the fields and a recorded response.
Sources
What this page says of other services is from their own pages and documents, read on 2026-11-04.
- QwenWork: connectors
Start with one key.
237 endpoints on 21 platforms, from $0.0003 a call. Errors and timeouts are not charged.