DataSocial

Query a TikTok data warehouse (creators, videos, sounds, daily history) with read-only SQL.

¿Debería usar esto?

Calidad y seguridad

A
Calidad de la descripción
95%
Integridad del esquema
80%
Calidad de los nombres
90%
Riesgo de envenenamiento
100%
Coincidencia de permisos
100%
Cumplimiento del protocolo
100%

Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.

Costo de contexto

~810Tokens (definiciones de herramientas)
~1.7 KBTamaño de respuesta típico
Impacto moderado en la atención (0.63% del contexto de 128k)

Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.

Instalar

Instalación con un clic

Agrega esto a tu archivo `claude_desktop_config.json`:

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

Puntos de conexión remotos

https://api.datasocial.ai/mcpstreamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (4)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢list_tables

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

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "tables": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "table": {
            "type": "string"
          },
          "rows": {
            "type": "string"
          },
          "one_row_is": {
            "type": [
              "string",
              "null"
            ]
          },
          "about": {
            "type": [
              "string",
              "null"
            ]
          }
        },
        "required": [
          "table",
          "rows",
          "one_row_is",
          "about"
        ],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "tables"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}
🟢describe_table(table)

One table's columns with types and meanings, its sort key and coverage. Read it before writing SQL on a table.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "table": {
      "type": "string",
      "description": "The table, e.g. \"creators\" or \"tiktok.creators\""
    }
  },
  "required": [
    "table"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "table": {
      "type": "string"
    },
    "description": {
      "type": "string",
      "description": "Size, grain, sort key, coverage and every column with its type and meaning"
    }
  },
  "required": [
    "table",
    "description"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}
🟢examples(table)

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.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "table": {
      "description": "Only examples on this table, e.g. \"sound_history\"; omit for all",
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "examples": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "table": {
            "type": "string"
          },
          "question": {
            "type": "string"
          },
          "sql": {
            "type": "string"
          }
        },
        "required": [
          "table",
          "question",
          "sql"
        ],
        "additionalProperties": false
      }
    },
    "sql_tips": {
      "type": "string"
    }
  },
  "required": [
    "examples",
    "sql_tips"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}
🟢run_sql(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.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "sql": {
      "type": "string",
      "maxLength": 100000,
      "description": "One ClickHouse SELECT, e.g. SELECT username, followers FROM tiktok.creators WHERE country = 'US' ORDER BY followers DESC LIMIT 10"
    }
  },
  "required": [
    "sql"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "columns": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "rows": {
      "type": "array",
      "items": {
        "type": "array",
        "items": {}
      },
      "description": "One array per row, values in the order of columns"
    },
    "capped": {
      "type": "boolean",
      "description": "true when the result was cut at the 100-row limit"
    },
    "rows_read": {
      "type": "number"
    },
    "elapsed_ms": {
      "type": "number"
    }
  },
  "required": [
    "columns",
    "rows",
    "capped",
    "rows_read",
    "elapsed_ms"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada4 herramientas