DataSocial
by datasocial.ai in News & content
Query a TikTok data warehouse (creators, videos, sounds, daily history) with read-only SQL.
https://api.datasocial.ai/mcp
Last 30 days
- Uptime
- 100%
- Response time
- 675 ms typical, 675 ms slowest 5%
- Last check
- 4 h ago
- Next check
- in 3 h
How to call it
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"datasocial": {
"type": "http",
"url": "https://api.datasocial.ai/mcp"
}
}
}4 tools
- list_tables
The tables in the DataSocial TikTok warehouse: name, row count, what one row is, and what it holds.
- describe_table
One table's columns with types and meanings, its sort key and coverage. Read it before writing SQL on a table.
- examples
Worked examples (a question and SQL that runs here) and the SQL tips: growth maths, history-table patterns, big sound_history days, follows lookups. Pass a table to get only its examples.
- run_sql
Run one read-only ClickHouse SELECT on tiktok.* and get the rows back (at most 100 per request; 10 s per query). Name the columns you need and add a LIMIT.
Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 4 h ago | Passed | 200 | 675 ms |
| 12 h ago | Passed | 200 | 1.3 s |