Get foreign key relationships for tables
AI agents call get_relationships to retrieve information from MCP PostgreSQL Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves schema metadata (foreign key relationships) without side effects. It is purely informational and read-only, consistent with the server's stated read-only access model. No data is created, modified, deleted, or executed.
From the tool's definition Tool description states 'Get foreign key relationships for tables' and server description emphasizes 'secure read-only access' and 'query schemas' and 'inspect table structures'. The tool retrieves metadata about table relationships without modifying data.
Attacks that exploit this kind of access
Get foreign key relationships for tables. It is categorised as a Read tool in the MCP PostgreSQL Server MCP Server, which means it retrieves data without modifying state.
Register the MCP PostgreSQL Server MCP server in PolicyLayer and add a rule for get_relationships: 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 MCP PostgreSQL Server. Nothing to install.
get_relationships 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_relationships 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_relationships. 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_relationships is provided by the MCP PostgreSQL Server MCP server (kristofer84/mcp-postgres). 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 →