AI agents use schema_undo to create or update resources in Zion — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zion environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
appExId | string | null | — | |
projectExId | string | — | |
appVersionExId | string | null | — |
Parameters from the server's own tool schema.
This tool modifies schema state by applying reverse patches, which is a Write operation (reversible modification). It is not Destructive because the changes can be undone via schema_redo, and concurrent-edit conflicts are explicitly guarded against. Severity is medium because schema modifications could affect application structure, but the reversibility and conflict-checking mitigate blast radius.
From the tool's definition Tool applies a 'reverse CRDT patch' to undo schema changes, modifying data (schema) reversibly. Description states it 'Undo[s] the most recent schema change' and 'Pairs with schema_redo', indicating Write operations that can be undone/redone.
Attacks that exploit this kind of access
Undo the most recent schema change made in this session by applying a reverse CRDT patch. Refuses if a concurrent edit touched the same path. Pairs with schema_redo. It is categorised as a Write tool in the Zion MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
schema_undo accepts 3 parameters: appExId, projectExId, appVersionExId. The full parameter table on this page comes from the server's own tool schema.
Register the Zion MCP server in PolicyLayer and add a rule for schema_undo: 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 Zion. Nothing to install.
schema_undo 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 schema_undo 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 schema_undo. 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.
schema_undo is provided by the Zion MCP server (zion-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 →