AI agents call list_schemas to retrieve information from Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves schema metadata from a PostgreSQL database without creating, modifying, or deleting any data. It is a simple informational query with no side effects, making it a Read category tool. Severity is low because schema names are generally non-sensitive metadata, and exposure carries minimal risk even if accessed by an unauthorized agent.
From the tool's definition Tool name 'list_schemas' and description 'List all non-system database schemas' indicate a retrieval operation with no side effects. The server is described as 'optimized for...read-only queries' and this tool lists metadata, not modifying data.
Attacks that exploit this kind of access
List all non-system database schemas. It is categorised as a Read tool in the Postgres MCP Server, which means it retrieves data without modifying state.
Register the Postgres MCP server in PolicyLayer and add a rule for 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 Postgres. Nothing to install.
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 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 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.
list_schemas is provided by the Postgres MCP server (madhurprash/postgres-mcp-agentcore). 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 →