Safely execute a read-only SQL query and retrieve results
AI agents call query_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 is explicitly constrained to read-only SQL queries (SELECT operations). It retrieves or queries data from PostgreSQL databases without creating, modifying, or deleting data. While the sibling execute_tool and transaction_tool on this server could be Execute or Destructive, query_tool itself is limited to data retrieval, making it a Read-category tool with low severity.
From the tool's definition Tool name 'query_tool' and description 'Safely execute a read-only SQL query and retrieve results' explicitly indicate read-only operations that retrieve data without side effects.
Attacks that exploit this kind of access
Safely execute a read-only SQL query and retrieve results. 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 query_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.
query_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 query_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 query_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.
query_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 →