Find what depends on a database object before dropping it. Recursively walks pg_depend, classifies dependents (views, foreign keys, functions, materialized views, indexes, rules) and reports each with its depth from the target. Use this BEFORE running DROP CASCADE to understand the blast radius. ...
AI agents call find_dependents 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.
find_dependents performs schema dependency querying without modifying, deleting, or executing any database operations. It retrieves metadata about object dependencies to inform decision-making. There are no side effects—it only analyzes and returns information. This is a classic Read operation (fetch/query metadata).
From the tool's definition Tool description states it 'Find[s] what depends on a database object' and 'Recursively walks pg_depend', 'classifies dependents', and 'reports each with its depth'.
Attacks that exploit this kind of access
Find what depends on a database object before dropping it. Recursively walks pg_depend, classifies dependents (views, foreign keys, functions, materialized views, indexes, rules) and reports each with its depth from the target. Use this BEFORE running DROP CASCADE to understand the blast radius. Returns the dependent objects flattened with. 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 find_dependents: 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.
find_dependents 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 find_dependents 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 find_dependents. 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.
find_dependents is provided by the Postgres MCP server (teja-sudo/postgres-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 →