pg_security_sensitive_tables
Identify tables and columns that may contain sensitive data based on column name patterns.
This record as markdown: /tools/io-github-neverinfamous-postgres-mcp/pg-security-sensitive-tables.md
What pg_security_sensitive_tables does on PostgreSQL MCP Server
AI agents call pg_security_sensitive_tables to retrieve information from PostgreSQL MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why pg_security_sensitive_tables is rated Low
This tool retrieves and queries metadata about table structures and column names to classify them as potentially sensitive. It performs no modifications, deletions, or external operations—purely informational analysis. The severity is low because even if an AI agent calls this tool, it only discovers information about schema structure based on naming conventions, with no ability to access actual data or cause damage.
From the tool's definition Tool name contains 'Identify' and description states 'Identify tables and columns...based on column name patterns' — performs pattern-matching inspection without modifying data.
Attacks that exploit this kind of access
The rule that runs pg_security_sensitive_tables safely
PolicyLayer is an MCP gateway: it sits between your AI agents and PostgreSQL MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pg_security_sensitive_tables, this is the rule to start with:
pg_security_sensitive_tables is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect PostgreSQL MCP Server, apply this rule, and every pg_security_sensitive_tables call is checked against it from then on.
Questions about pg_security_sensitive_tables
Identify tables and columns that may contain sensitive data based on column name patterns. It is categorised as a Read tool in the PostgreSQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PostgreSQL MCP Server MCP server in PolicyLayer and add a rule for pg_security_sensitive_tables: 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 PostgreSQL MCP Server. Nothing to install.
pg_security_sensitive_tables 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 pg_security_sensitive_tables 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 pg_security_sensitive_tables. 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.
pg_security_sensitive_tables is provided by the PostgreSQL MCP Server MCP server (@neverinfamous/postgres-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on PostgreSQL MCP Server, and thousands of servers like it.
This server
Across the catalogue