Show detailed information about a database object
AI agents call get_object_details to retrieve information from Fluid Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about database objects (schemas, tables, columns, constraints, etc.) without executing code, modifying data, or triggering side effects. It is a passive inspection tool suitable for gathering information about database structure.
From the tool's definition Tool name 'get_object_details' and description 'Show detailed information about a database object' indicate a query/retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Show detailed information about a database object. It is categorised as a Read tool in the Fluid Postgres MCP Server, which means it retrieves data without modifying state.
Register the Fluid Postgres MCP server in PolicyLayer and add a rule for get_object_details: 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 Fluid Postgres. Nothing to install.
get_object_details 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 get_object_details 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 get_object_details. 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.
get_object_details is provided by the Fluid Postgres MCP server (povesma/fluid-postgres-mcp). 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 →