AI agents use create_transformation to create or update resources in Zhook — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zhook environment.
This tool creates new transformation rules that will be applied to webhook data processing. While it creates/modifies configuration (Write category), the severity is medium rather than high because: (1) transformations are reversible via deletion or updates, (2) the blast radius is limited to data transformation logic rather than direct data deletion or financial operations, and (3) misuse could corrupt data flows…
From the tool's definition Tool name 'create_transformation' and description 'Create a new JSONata transformation for a hook' indicate creation of configuration data that modifies hook behavior.
Attacks that exploit this kind of access
Create a new JSONata transformation for a hook. It is categorised as a Write tool in the Zhook MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zhook MCP server in PolicyLayer and add a rule for create_transformation: 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 Zhook. Nothing to install.
create_transformation 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 create_transformation 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 create_transformation. 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.
create_transformation is provided by the Zhook MCP server (zhookteam/zhook-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 →