Inspect PostgreSQL schema: tables, columns, indexes, constraints, and sizes.
AI agents call pg_schema to retrieve information from RedisNexus 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 database schema metadata without creating, modifying, deleting, executing code, or moving data. It is a passive inspection capability typical of database administrative read operations. The blast radius of misuse is minimal—an agent could gather schema knowledge but cannot alter data or structure.
From the tool's definition Tool description states 'Inspect PostgreSQL schema' and lists read-only operations: 'tables, columns, indexes, constraints, and sizes.' The verb 'inspect' and the informational nature of schema metadata retrieval indicate no modifications or side effects.
Attacks that exploit this kind of access
Inspect PostgreSQL schema: tables, columns, indexes, constraints, and sizes. It is categorised as a Read tool in the RedisNexus MCP Server, which means it retrieves data without modifying state.
Register the RedisNexus MCP server in PolicyLayer and add a rule for pg_schema: 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 RedisNexus. Nothing to install.
pg_schema 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_schema 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_schema. 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_schema is provided by the RedisNexus MCP server (rajkumar-madhu/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 →