Execute a DML statement (INSERT/UPDATE/DELETE) on Oracle database.
AI agents invoke execute_dml to trigger actions in Springboot Test. 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.
While DML operations (INSERT/UPDATE/DELETE) are reversible and thus not Destructive in the strict sense, they are Execute-category tools because they modify data irreversibly within a transaction context and their effects depend on the specific DML arguments provided.
From the tool's definition Tool executes DML statements (INSERT/UPDATE/DELETE) on Oracle database. The description explicitly names these data modification operations, which are executable statements with side effects.
Attacks that exploit this kind of access
Execute a DML statement (INSERT/UPDATE/DELETE) on Oracle database. It is categorised as a Execute tool in the Springboot Test MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Springboot Test MCP server in PolicyLayer and add a rule for execute_dml: 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 Springboot Test. Nothing to install.
execute_dml 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 execute_dml 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 execute_dml. 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.
execute_dml is provided by the Springboot Test MCP server (kenlin-7/springboot-test-mcp). 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 →