执行 SELECT 查询（只读模式），返回 Markdown 表格格式的结果
AI agents call query to retrieve information from MCP DB Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves data via SELECT queries in read-only mode with built-in safety checks. It cannot modify, delete, or execute arbitrary operations. The read-only constraint and explicit mention of safety checks place this firmly in the Read category with low severity, as the blast radius of misuse is limited to information disclosure.
From the tool's definition Tool name 'query' with description stating '执行 SELECT 查询（只读模式）' (Execute SELECT query in read-only mode), explicitly limited to SELECT operations and returns results in Markdown table format. Server description confirms 'read-only safety checks'.
Attacks that exploit this kind of access
执行 SELECT 查询（只读模式），返回 Markdown 表格格式的结果. It is categorised as a Read tool in the MCP DB Server MCP Server, which means it retrieves data without modifying state.
Register the MCP DB Server 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 DB Server. 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 DB Server MCP server (sharpdogs/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 →