Execute any SQL query including INSERT, UPDATE, DELETE (use with caution)
AI agents invoke execute_raw_query to trigger actions in MCP PostgreSQL Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
While DELETE operations could warrant Destructive classification, the tool's primary function is executing arbitrary SQL queries with effects dependent on the query argument. This is Execute-category risk. The (use with caution) warning and the tool's presence on a read-only server suggests it may be gated, but the capability remains.
From the tool's definition Tool description explicitly states 'Execute any SQL query including INSERT, UPDATE, DELETE (use with caution)', and the name is 'execute_raw_query'.
Attacks that exploit this kind of access
Execute any SQL query including INSERT, UPDATE, DELETE (use with caution). It is categorised as a Execute tool in the MCP PostgreSQL Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP PostgreSQL Server MCP server in PolicyLayer and add a rule for execute_raw_query: 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 PostgreSQL Server. Nothing to install.
execute_raw_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_raw_query 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 execute_raw_query. 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.
execute_raw_query is provided by the MCP PostgreSQL Server MCP server (kristofer84/mcp-postgres). 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 →