Insert a single record into a table. Returns the new row
AI agents use insert_record to create or update resources in Instant Db — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Instant Db environment.
This tool creates new data (writes a record to a database table) with reversible effects—the record can be deleted via the delete_record sibling tool. It is not destructive (irreversible deletion), not financial, and not Execute (it doesn't run arbitrary code or shell commands, just structured data insertion). Write is the appropriate classification.
From the tool's definition Tool name 'insert_record' and description 'Insert a single record into a table. Returns the new row' clearly indicate data creation and modification.
Attacks that exploit this kind of access
Insert a single record into a table. Returns the new row. It is categorised as a Write tool in the Instant Db MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Instant Db MCP server in PolicyLayer and add a rule for insert_record: 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.
insert_record is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the insert_record 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 insert_record. 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.
insert_record 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 →