Server definition

Hash: sha256:1d4e6b64b212d1007afc80fce1538a41b7aa11b67a314f572b76f98defdb1251
What it is: What a remote MCP server returned when asked what it offers: 4 tools

The blob, as servednamed by its sha256

{
  "instructions": "DataSocial is a TikTok data warehouse (ClickHouse): billions of creators, videos and sounds, with daily history.\nStart with list_tables, then describe_table for the columns you need and examples for worked SQL on that table, then run_sql.\nRules: one read-only SELECT on tiktok.<table>; name the columns; always a LIMIT;\nat most 100 rows per request; 10 s per query. Filter the huge tables on their sort key (creators: country, then followers).\nHistory tables hold one row per id per date: the latest day is (SELECT max(date) FROM tiktok.<table>).\nGrowth % = (now - previous) / previous * 100. ids are strings (they exceed 2^53).\ntiktok.follows is a lookup, not a table: FROM tiktok.follows(creator_id = <id>) gives who that creator follows.\nEmails: creators.email is '[email hidden]' when we have one (has_email, email_domain say which); addresses in bios and\ncaptions are hidden too. For the 31M creator emails (sold privately) or the full database without the 100-row limit:\nhttps://datasocial.ai/buy",
  "tools": [
    {
      "description": "One table's columns with types and meanings, its sort key and coverage. Read it before writing SQL on a table.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "table": {
            "description": "The table, e.g. \"creators\" or \"tiktok.creators\"",
            "type": "string"
          }
        },
        "required": [
          "table"
        ],
        "type": "object"
      },
      "name": "describe_table",
      "outputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "description": {
            "description": "Size, grain, sort key, coverage and every column with its type and meaning",
            "type": "string"
          },
          "table": {
            "type": "string"
          }
        },
        "required": [
          "table",
          "description"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "table": {
            "description": "Only examples on this table, e.g. \"sound_history\"; omit for all",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "examples",
      "outputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "examples": {
            "items": {
              "additionalProperties": false,
              "properties": {
                "question": {
                  "type": "string"
                },
                "sql": {
                  "type": "string"
                },
                "table": {
                  "type": "string"
                }
              },
              "required": [
                "table",
                "question",
                "sql"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "sql_tips": {
            "type": "string"
          }
        },
        "required": [
          "examples",
          "sql_tips"
        ],
        "type": "object"
      }
    },
    {
      "description": "The tables in the DataSocial TikTok warehouse: name, row count, what one row is, and what it holds.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "list_tables",
      "outputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "tables": {
            "items": {
              "additionalProperties": false,
              "properties": {
                "about": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "one_row_is": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "rows": {
                  "type": "string"
                },
                "table": {
                  "type": "string"
                }
              },
              "required": [
                "table",
                "rows",
                "one_row_is",
                "about"
              ],
              "type": "object"
            },
            "type": "array"
          }
        },
        "required": [
          "tables"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "sql": {
            "description": "One ClickHouse SELECT, e.g. SELECT username, followers FROM tiktok.creators WHERE country = 'US' ORDER BY followers DESC LIMIT 10",
            "maxLength": 100000,
            "type": "string"
          }
        },
        "required": [
          "sql"
        ],
        "type": "object"
      },
      "name": "run_sql",
      "outputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "capped": {
            "description": "true when the result was cut at the 100-row limit",
            "type": "boolean"
          },
          "columns": {
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "elapsed_ms": {
            "type": "number"
          },
          "rows": {
            "description": "One array per row, values in the order of columns",
            "items": {
              "items": {},
              "type": "array"
            },
            "type": "array"
          },
          "rows_read": {
            "type": "number"
          }
        },
        "required": [
          "columns",
          "rows",
          "capped",
          "rows_read",
          "elapsed_ms"
        ],
        "type": "object"
      }
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:1d4e6b64b212d1007afc80fce1538a41b7aa11b67a314f572b76f98defdb1251 | sha256sum