AI agents call kb_list_schemas 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.
This tool queries database metadata (schema names and owners) without modifying, deleting, or executing operations. It is purely informational retrieval, fitting the Read category. Low severity because schema enumeration alone poses minimal risk unless combined with other tools to target specific data.
From the tool's definition Tool name 'kb_list_schemas' and description 'List all schemas in the KingBase database' indicates a retrieval operation with no side effects. Returns schema names and owners; takes no arguments that could modify state.
Attacks that exploit this kind of access
List all schemas in the KingBase database. Returns schema names excluding internal PostgreSQL/KingBase system schemas. Args: None Returns: List of schema names with their owners. It is categorised as a Read tool in the Kingbase MCP Server, which means it retrieves data without modifying state.
Register the Kingbase MCP server in PolicyLayer and add a rule for kb_list_schemas: 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_list_schemas 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_list_schemas 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_list_schemas. 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_list_schemas 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 →