AI agents call select_database to retrieve information from QueryNest without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool discovers and selects a database to work with — it reads/discovers available databases and sets a session-level selection. The description emphasizes auto-discovery and providing recommendations with user confirmation, implying no data modification. It is analogous to a 'USE database' command, which is a session state change rather than a destructive or write operation.
From the tool's definition 智能数据库选择工具：自动发现数据库并提供推荐选项，需要用户确认后执行 (Intelligent database selection tool: automatically discovers databases and provides recommended options, requires user confirmation before execution)
Attacks that exploit this kind of access
智能数据库选择工具：自动发现数据库并提供推荐选项，需要用户确认后执行. It is categorised as a Read tool in the QueryNest MCP Server, which means it retrieves data without modifying state.
Register the QueryNest MCP server in PolicyLayer and add a rule for select_database: 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 QueryNest. Nothing to install.
select_database 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 select_database 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 select_database. 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.
select_database is provided by the QueryNest MCP server (niuzaishu/querynest). 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 →