Retrieve detailed schema information for a specific table
AI agents call schema_tool to retrieve information from FastPostgresMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns metadata about database table structure. It performs no modifications, deletions, or code execution. The blast radius of misuse is minimal—an agent could only learn about table structures, which is informational only.
From the tool's definition Tool name 'schema_tool' and description 'Retrieve detailed schema information for a specific table' indicate a read-only operation. The verb 'retrieve' and the context of inspecting schemas (not modifying them) confirm no side effects.
Attacks that exploit this kind of access
Retrieve detailed schema information for a specific table. It is categorised as a Read tool in the FastPostgresMCP MCP Server, which means it retrieves data without modifying state.
Register the FastPostgres MCP server in PolicyLayer and add a rule for schema_tool: 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 FastPostgresMCP. Nothing to install.
schema_tool 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 schema_tool 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 schema_tool. 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.
schema_tool is provided by the FastPostgres MCP server (llm-graph/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 →