Execute a read-only SQL query
AI agents call query to retrieve information from MCP Server Templates without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data via SQL without the ability to modify, delete, or execute arbitrary operations. Read-only SQL queries are inherently non-destructive and fall clearly into the Read category. Severity is low because the blast radius of misuse is limited to unauthorized information disclosure, which is less severe than data modification or deletion.
From the tool's definition Tool name is "query" and description explicitly states "Execute a read-only SQL query". The "read-only" qualifier directly constrains the tool to data retrieval with no side effects.
Attacks that exploit this kind of access
Execute a read-only SQL query. It is categorised as a Read tool in the MCP Server Templates MCP Server, which means it retrieves data without modifying state.
Register the MCP Server Templates MCP server in PolicyLayer and add a rule for 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 Server Templates. Nothing to install.
query 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 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. 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 is provided by the MCP Server Templates MCP server (visystems/mcp-server-templates). 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 →