Execute a DML statement (INSERT/UPDATE/DELETE) against a database. DDL and SELECT are rejected. Runs inside a transaction.
AI agents invoke execute_mutation to trigger actions in Instant Db. 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.
This tool executes arbitrary DML statements (INSERT, UPDATE, DELETE) against a database. While it rejects DDL and SELECT, it can still modify or delete data at scale through arbitrary UPDATE/DELETE statements. DELETE operations make this potentially destructive, but since it runs inside a transaction (implying rollback capability), it sits at Execute/Destructive boundary.
From the tool's definition Execute a DML statement (INSERT/UPDATE/DELETE) against a database... Runs inside a transaction.
Attacks that exploit this kind of access
Execute a DML statement (INSERT/UPDATE/DELETE) against a database. DDL and SELECT are rejected. Runs inside a transaction. It is categorised as a Execute tool in the Instant Db MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Instant Db MCP server in PolicyLayer and add a rule for execute_mutation: 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 Instant Db. Nothing to install.
execute_mutation 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_mutation 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_mutation. 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_mutation is provided by the Instant Db MCP server (urbushey/mcp-db). 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 →