Analytics

datasocial.ai

A read-only ClickHouse analytics MCP server for querying a DataSocial TikTok warehouse, exposing table listing, schema description, SQL examples, and a run_sql tool for running SELECT queries.

1 endpoint4 known toolsFirst detected October 1, 2026Last detected October 1, 2026

ENDPOINT 1

https://api.datasocial.ai/mcp

No auth detected

MCP server metadata

Name: datasocial
Version: 1.0.0

Capabilities

tools.listChanged

Server instructions

DataSocial is a TikTok data warehouse (ClickHouse): billions of creators, videos and sounds, with daily history. Start with list_tables, then describe_table for the columns you need and examples for worked SQL on that table, then run_sql. Rules: one read-only SELECT on tiktok.<table>; name the columns; always a LIMIT; at most 100 rows per request; 10 s per query. Filter the huge tables on their sort key (creators: country, then followers). History tables hold one row per id per date: the latest day is (SELECT max(date) FROM tiktok.<table>). Growth % = (now - previous) / previous * 100. ids are strings (they exceed 2^53). tiktok.follows is a lookup, not a table: FROM tiktok.follows(creator_id = <id>) gives who that creator follows. Emails: creators.email is '[email hidden]' when we have one (has_email, email_domain say which); addresses in bios and captions are hidden too. For the 31M creator emails (sold privately) or the full database without the 100-row limit: https://datasocial.ai/buy

Known tools 4

list_tables

The tables in the DataSocial TikTok warehouse: name, row count, what one row is, and what it holds.

Inferred read-only

describe_table

One table's columns with types and meanings, its sort key and coverage.

Inferred read-only

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.

Inferred read-only

run_sql

Run one read-only ClickHouse SELECT on tiktok.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.datasocial]
url = "https://api.datasocial.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "datasocial": {
      "type": "http",
      "url": "https://api.datasocial.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: datasocial
Remote MCP URL: https://api.datasocial.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "datasocial": {
      "url": "https://api.datasocial.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "datasocial": {
      "type": "http",
      "url": "https://api.datasocial.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "datasocial",
  "transport": "streamable-http",
  "url": "https://api.datasocial.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for datasocial.ai was fetched 2026-10-03T07:06:09.108Z.

Trust status Neutral

datasocial.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.