AI agents invoke query_dameng to trigger actions in Dameng. 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.
The tool executes arbitrary SQL including DML statements (INSERT, UPDATE, DELETE), which can modify or destroy data. Since it supports both read queries and data-manipulation statements, it spans Read through potentially Destructive categories. The most severe applicable category is Execute (DML can modify data reversibly or irreversibly depending on the statement).
From the tool's definition 执行达梦数据库 SQL 查询(SELECT/DML),返回结构化结果 — explicitly supports DML (INSERT/UPDATE/DELETE) in addition to SELECT
Attacks that exploit this kind of access
执行达梦数据库 SQL 查询(SELECT/DML),返回结构化结果. It is categorised as a Execute tool in the Dameng MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Dameng MCP server in PolicyLayer and add a rule for query_dameng: 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 Dameng. Nothing to install.
query_dameng 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 query_dameng 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_dameng. 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_dameng is provided by the Dameng MCP server (springdamon/mcp-server-dameng). 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 →