Enum and object-type definitions. Create an enum before any column that references it; editing in-use options is destructive (prefer ADDING). Changes apply immediately; use schema_undo to revert the last change. Ops: - op=ADD_ENUMS → ADD_ENUM_DEFINITIONS (req: enums) [post-type-system-refactor on...
AI agents use schema_type 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 |
|---|---|---|---|
op | string | Yes | |
enums | object | — | |
types | object | — | |
fields | array | — | |
typeId | string | — | |
appExId | string | null | — | |
enumIds | array | — | |
typeIds | array | — | |
fieldNames | array | — | |
projectExId | string | — | |
appVersionExId | string | null | — |
Parameters from the server's own tool schema.
Primary operations (ADD_ENUMS, ADD_OBJECTS, ADD_FIELDS) are reversible Write actions that create/modify schema definitions. While DELETE operations exist, the tool is classified as Write rather than Destructive because the description emphasizes schema_undo capability for reverting changes, and the dominant use case is additive modification.
From the tool's definition Tool performs ADD_ENUMS, ADD_OBJECTS, ADD_FIELDS operations that create/modify type definitions; description explicitly states 'Changes apply immediately' and warns that 'editing in-use options is destructive (prefer ADDING)', indicating persistent data…
Risk signalsHigh parameter count (11 properties)
Attacks that exploit this kind of access
Enum and object-type definitions. Create an enum before any column that references it; editing in-use options is destructive (prefer ADDING). Changes apply immediately; use schema_undo to revert the last change. Ops: - op=ADD_ENUMS → ADD_ENUM_DEFINITIONS (req: enums) [post-type-system-refactor only] - op=ADD_OBJECTS → ADD_OBJECT_TYPE_DEFINITIONS (req: types) [post-type-system-refactor only] - op=ADD_FIELDS → ADD_TYPE_DEFINITION_FIELDS (req: fields, typeId) [post-type-system-refactor only] - op=DELETE_ENUMS → DELETE_ENUM_DEFINITIONS (req: enumIds) [post-type-system-refactor only] - op=DELETE_OBJECTS → DELETE_OBJECT_TYPE_DEFINITIONS (req: typeIds) [post-type-system-refactor only] - op=DELETE_FIELDS → DELETE_TYPE_DEFINITION_FIELDS (req: fieldNames, typeId) [post-type-system-refactor only] - op=LIST_ENUMS → GET_ALL_ENUM_DEFINITIONS [post-type-system-refactor only] - op=LIST_OBJECTS → GET_ALL_OBJECT_DEFINITIONS [post-type-system-refactor only] - op=UPDATE_ENUMS → UPDATE_ENUM_DEFINITIONS (req: enums) [post-type-system-refactor only] - op=UPDATE_OBJECTS → UPDATE_OBJECT_TYPE_DEFINITIONS (req: types) [post-type-system-refactor only]. 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_type accepts 11 parameters: op, enums, types, fields, typeId, appExId, enumIds, typeIds, fieldNames, projectExId, appVersionExId. Required: op. 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_type: 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_type 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_type 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_type. 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_type 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 →