Execute a read-only SQL SELECT query and return results.
AI agents call query_table to retrieve information from MCP Database Query Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data through SELECT queries with no capability for modification, deletion, or side effects. The read-only constraint is clearly stated in both the tool and server descriptions. The blast radius of misuse is limited to unauthorized data access, which is a low-severity risk if secrets are exposed in databases.
From the tool's definition Tool name 'query_table' and description 'Execute a read-only SQL SELECT query and return results' explicitly restrict to SELECT statements only.
Attacks that exploit this kind of access
Execute a read-only SQL SELECT query and return results. It is categorised as a Read tool in the MCP Database Query Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Database Query Server MCP server in PolicyLayer and add a rule for query_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 Database Query Server. Nothing to install.
query_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 query_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 query_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.
query_table is provided by the MCP Database Query Server MCP server (vicus-brits/mcp-server). 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 →