MCP Tool Schemas

JSON input schemas for all six MCP tools registered with the Metatate MCP server. Each tool is exposed as either a UDF or stored procedure in the core schema and made available to AI agents via the Snowflake MCP protocol.

discover_context

Discover tables in the governed catalog. All parameters are optional; omit everything to browse the full catalog.

{
  "type": "object",
  "properties": {
    "database": {
      "type": "string",
      "description": "Filter by database name"
    },
    "schema": {
      "type": "string",
      "description": "Filter by schema name"
    },
    "min_sensitivity": {
      "type": "string",
      "enum": ["PUBLIC", "INTERNAL", "CONFIDENTIAL", "RESTRICTED"],
      "description": "Minimum sensitivity level to include"
    },
    "compliance_any": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Include tables matching any of these compliance frameworks (e.g. GDPR, HIPAA, SOX)"
    },
    "has_pii": {
      "type": "boolean",
      "description": "Filter to tables that contain PII columns"
    },
    "domain": {
      "type": "string",
      "description": "Filter by business domain"
    }
  },
  "required": []
}

get_decision_context

Retrieve the full governance context for a specific table, including policies, classifications, sensitivity, and compliance metadata.

{
  "type": "object",
  "properties": {
    "table_name": {
      "type": "string",
      "description": "Fully qualified table name (DATABASE.SCHEMA.TABLE)"
    }
  },
  "required": ["table_name"]
}

inspect_data_meaning

Inspect column-level metadata including data types, classifications, masking policies, and PII flags.

{
  "type": "object",
  "properties": {
    "table_name": {
      "type": "string",
      "description": "Fully qualified table name (DATABASE.SCHEMA.TABLE)"
    },
    "columns": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Specific column names to inspect. Omit to inspect all columns."
    }
  },
  "required": ["table_name"]
}

authorize_use

Check whether a proposed data operation is authorized under current governance policies. Returns an allow/deny decision with reasoning.

{
  "type": "object",
  "properties": {
    "table_name": {
      "type": "string",
      "description": "Fully qualified table name (DATABASE.SCHEMA.TABLE)"
    },
    "operation": {
      "type": "string",
      "enum": ["SELECT", "INSERT", "UPDATE", "DELETE", "EXPORT", "SHARE"],
      "description": "The data operation being requested"
    },
    "intended_use": {
      "type": "string",
      "description": "Plain-language description of why the data is needed"
    },
    "actor_role": {
      "type": "string",
      "description": "Snowflake role performing the operation"
    },
    "columns": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Specific columns involved in the operation"
    },
    "destination": {
      "type": "string",
      "description": "Where the data will be sent or stored"
    },
    "jurisdiction": {
      "type": "string",
      "description": "Legal jurisdiction for the operation (e.g. EU, US-CA)"
    },
    "context": {
      "type": "object",
      "description": "Additional context as key-value pairs"
    }
  },
  "required": ["table_name", "operation", "intended_use"]
}

validate_query_context

Validate a SQL query against all applicable governance policies before execution. Returns issues, warnings, and suggested rewrites.

{
  "type": "object",
  "properties": {
    "sql": {
      "type": "string",
      "description": "The SQL query to validate"
    },
    "operation": {
      "type": "string",
      "enum": ["SELECT", "INSERT", "UPDATE", "DELETE", "EXPORT", "SHARE"],
      "description": "The operation type (inferred from SQL if omitted)"
    },
    "intended_use": {
      "type": "string",
      "description": "Plain-language description of the query's purpose"
    },
    "actor_role": {
      "type": "string",
      "description": "Snowflake role that will execute the query"
    }
  },
  "required": ["sql"]
}

explain_why

Retrieve a detailed explanation of a previous authorization or validation decision, including the policies evaluated and reasoning chain.

{
  "type": "object",
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "The unique decision ID returned by authorize_use or validate_query_context"
    }
  },
  "required": ["decision_id"]
}