Preview data from a table with optional filtering and pagination. A convenient shortcut for common SELECT operations without writing full SQL. Args: - table (string): Table name - schema (string, optional): Schema name, defaults to DB_SCHEMA env or 'public' - limit (number, default 100, max 1000)...
AI agents call kb_table_data to retrieve information from Kingbase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | Number of rows to return (default: 100, max: 1000) |
table | string | Yes | Table name to preview data from |
where | string | — | Optional WHERE clause (without the WHERE keyword), e.g. "status = 'active'" |
offset | integer | — | Number of rows to skip (default: 0) |
schema | string | — | Schema name (default: from DB_SCHEMA env or 'public') |
order_by | string | — | Optional ORDER BY clause (without the ORDER BY keyword), e.g. "created_at DESC" |
Parameters from the server's own tool schema.
This tool retrieves and displays existing data without side effects. It is functionally equivalent to a SELECT query with filtering and pagination. No data is created, modified, deleted, or overwritten. No code execution or financial operations occur. It poses minimal risk as read-only operations on a database cannot cause harm beyond potential information disclosure, which is inherent to database access control.
From the tool's definition Tool description states it performs 'Preview data from a table with optional filtering and pagination' and is 'A convenient shortcut for common SELECT operations'.
Attacks that exploit this kind of access
Preview data from a table with optional filtering and pagination. A convenient shortcut for common SELECT operations without writing full SQL. Args: - table (string): Table name - schema (string, optional): Schema name, defaults to DB_SCHEMA env or 'public' - limit (number, default 100, max 1000): Number of rows - offset (number, default 0): Rows to skip - where (string, optional): WHERE condition (without WHERE keyword) - order_by (string, optional): ORDER BY clause (without ORDER BY keyword) Returns: Formatted table of row data with total count. Examples: - table: "users", limit: 10, where: "status = 'active'", order_by: "created_at DESC" - table: "orders", limit: 50, offset: 100. It is categorised as a Read tool in the Kingbase MCP Server, which means it retrieves data without modifying state.
kb_table_data accepts 6 parameters: limit, table, where, offset, schema, order_by. Required: table. The full parameter table on this page comes from the server's own tool schema.
Register the Kingbase MCP server in PolicyLayer and add a rule for kb_table_data: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Kingbase. Nothing to install.
kb_table_data is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the kb_table_data rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for kb_table_data. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
kb_table_data is provided by the Kingbase MCP server (kingbase-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →