About DataSocial
DataSocial is a hosted MCP server for querying a ClickHouse warehouse of TikTok creators, videos, sounds, and follow relationships. MCP clients can inspect tables and run read-only SQL, with a 100-row and 10-second query limit.
Key features
- 01TikTok creator, video, sound, and follow data
- 02Table and column inspection
- 03Read-only SQL queries
- 04Example questions and SQL guidance
Use cases
- 01Find creators with rapid follower growth
- 02Identify sounds used in new videos
- 03Explore a creator's follow relationships
- 04Compare video views across creator groups
MCP support
DataSocial exposes its hosted TikTok data warehouse through a stateless Streamable HTTP MCP endpoint. MCP clients can inspect the schema and run read-only `SELECT` queries, limited to 100 rows and 10 seconds.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.datasocial.ai/mcpclaude mcp add --transport http hashfunction-dev-datasocial https://api.datasocial.ai/mcp{"mcpServers":{"hashfunction-dev-datasocial":{"type":"http","url":"https://api.datasocial.ai/mcp"}}}Open in Cursor{"servers":{"hashfunction-dev-datasocial":{"type":"http","url":"https://api.datasocial.ai/mcp"}}}Open in VS Code{"mcpServers":{"hashfunction-dev-datasocial":{"type":"http","url":"https://api.datasocial.ai/mcp"}}}{"mcpServers":{"hashfunction-dev-datasocial":{"serverUrl":"https://api.datasocial.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://api.datasocial.ai/mcpAuth requiredTools
4This tool takes no parameters.
Details
From the project READMEDataSocial MCP: query TikTok data from Claude, Cursor or any MCP client
A hosted MCP server over a ClickHouse warehouse of TikTok data: 4.1B creators, 5.5B videos, 604M sounds and 113.7B follow edges (124.6B rows). Ask your AI assistant a question; it writes the SQL and runs it. Free.
- Endpoint:
https://api.datasocial.ai/mcp(Streamable HTTP, stateless) - Key: free. Sign in at datasocial.ai, open the MCP tab, and copy the command with your key already in it.
- Limits: 100 rows per query, 10 s per query, read-only.
Connect
Claude Code
claude mcp add --transport http datasocial https://api.datasocial.ai/mcp \
--header "Authorization: Bearer $DATASOCIAL_KEY"
Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"datasocial": {
"url": "https://api.datasocial.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_KEY" }
}
}
}
Claude Desktop (claude_desktop_config.json, via mcp-remote)
{
"mcpServers": {
"datasocial": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.datasocial.ai/mcp", "--header", "Authorization:${AUTH}"],
"env": { "AUTH": "Bearer YOUR_KEY" }
}
}
}
Tools
| Tool | What it does |
|---|---|
list_tables | The tables, their row counts and what one row is |
describe_table | One table's columns, types and sort key |
examples | Worked questions with SQL that runs, plus SQL tips |
run_sql | Runs one read-only SELECT (up to 100 rows) |
Things to ask
- "Which US creators with over 1M followers grew fastest this week?"
- "Which sounds are being used in the most new videos today?"
- "Who does @<username> follow?"
- "What's the average view count of videos by creators in Brazil with 100K–500K followers?"
Daily creator and video history started on 2026-09-26; sound history has 106 days since January 2026.
Also
- Plain SQL or plain-English search in the browser, no account: datasocial.ai
- How the data is collected: Scraping TikTok's mobile API at billions of records a day
- The full database without the 100-row limit, or the scraper code: datasocial.ai/buy
This repo holds documentation only; the server is hosted.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.