postgres_describe_table
AI agents call postgres_describe_table to retrieve information from MCP Server Project without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to describe/inspect database table structure, which is a read-only operation that retrieves metadata. Confidence is moderate (0.75) because the description is empty, making inference reliant on naming conventions and context from similar tools on the server.
From the tool's definition Tool name is 'postgres_describe_table' which typically retrieves table metadata/schema information. No description provided, but the naming convention and sibling tools (postgres_get_table_sample, postgres_list_tables) suggest it queries database structure…
Attacks that exploit this kind of access
postgres_describe_table. It is categorised as a Read tool in the MCP Server Project MCP Server, which means it retrieves data without modifying state.
Register the MCP Server Project MCP server in PolicyLayer and add a rule for postgres_describe_table: 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 Server Project. Nothing to install.
postgres_describe_table 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 postgres_describe_table 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 postgres_describe_table. 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.
postgres_describe_table is provided by the MCP Server Project MCP server (jamesunlocked/mcp_projects). 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 →