schema_actionflow · Zion MCP: Risk & Policy

WHAT IT DOES

What schema_actionflow does on Zion

AI agents call schema_actionflow to permanently remove resources in Zion — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

PARAMETERS

Parameter	Type	Required
`op`	string	Yes
`name`	string	—
`type`	object	—
`items`	array	—
`names`	array	—
`nodeId`	string	—
`appExId`	string \| null	—
`isAsync`	boolean	—
`newName`	string	—
`timeout`	number	—
`arrayLevel`	number	—
`displayName`	string	—

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why schema_actionflow needs a policy

An AI agent that decides to call schema_actionflow doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Zion is gone — there is no undo for destructive operations.

Risk signalsHigh parameter count (18 properties)

Attacks that exploit this kind of access

Questions about schema_actionflow

What does the schema_actionflow tool do? +

Action flows — flow-level (addressed by actionFlowId). Discover types via op=SELECTABLE_TYPES and ids via op=GET_DETAIL. AI nodes require isAsync=true. Changes apply immediately; use schema_undo to revert the last change. Ops: - op=ADD → ADD_ACTION_FLOWS (req: items) - op=ADD_GLOBAL_VARS → ADD_ACTION_FLOW_GLOBAL_VARIABLES (req: actionFlowId, items) - op=ADD_INPUT_PARAMS → ADD_ACTION_FLOW_INPUT_PARAMS (req: actionFlowId, items) - op=ADD_OUTPUT_FIELDS → ADD_ACTION_FLOW_OUTPUT_FIELDS (req: actionFlowId, items) [pre-type-system-refactor only] - op=ADD_CUSTOM_CODE_NODE_OUTPUT_VALUE → ADD_CUSTOM_CODE_NODE_OUTPUT_VALUE (req: actionFlowId, name, nodeId, type) [pre-type-system-refactor only] - op=CLEAR_OUTPUT → CLEAR_ACTION_FLOW_OUTPUT (req: actionFlowId) [post-type-system-refactor only] - op=CLEAR_CUSTOM_CODE_NODE_OUTPUT_TYPE → CLEAR_CUSTOM_CODE_NODE_OUTPUT_TYPE (req: actionFlowId, nodeId) [post-type-system-refactor only] - op=DELETE → DELETE_ACTION_FLOWS (req: actionFlowIds) - op=DELETE_GLOBAL_VARS → DELETE_ACTION_FLOW_GLOBAL_VARIABLES (req: actionFlowId, variableKeys) - op=DELETE_INPUT_PARAMS → DELETE_ACTION_FLOW_INPUT_PARAMS (req: actionFlowId, names) - op=DELETE_OUTPUT_FIELDS → DELETE_ACTION_FLOW_OUTPUT_FIELDS (req: actionFlowId, names) [pre-type-system-refactor only] - op=DELETE_CUSTOM_CODE_NODE_OUTPUT_VALUE → DELETE_CUSTOM_CODE_NODE_OUTPUT_VALUE (req: actionFlowId, name, nodeId) [pre-type-system-refactor only] - op=GET_DETAIL → GET_ACTION_FLOW_DETAIL (req: actionFlowId) - op=SELECTABLE_TYPES → GET_ACTION_FLOW_SELECTABLE_TYPES - op=LIST → GET_ALL_ACTION_FLOW_INFOS - op=SET_OUTPUT → SET_ACTION_FLOW_OUTPUT (req: actionFlowId, type) [post-type-system-refactor only] - op=SET_CUSTOM_CODE_NODE_OUTPUT_TYPE → SET_CUSTOM_CODE_NODE_OUTPUT_TYPE (req: actionFlowId, nodeId, type) [post-type-system-refactor only] - op=UPDATE → UPDATE_ACTION_FLOW (req: actionFlowId) - op=UPDATE_GLOBAL_VARS → UPDATE_ACTION_FLOW_GLOBAL_VARIABLES (req: actionFlowId, items) - op=UPDATE_INPUT_PARAMS → UPDATE_ACTION_FLOW_INPUT_PARAMS (req: actionFlowId, items) - op=UPDATE_CUSTOM_CODE_NODE_OUTPUT_VALUE → UPDATE_CUSTOM_CODE_NODE_OUTPUT_VALUE (req: actionFlowId, name, nodeId) [pre-type-system-refactor only]. It is categorised as a Destructive tool in the Zion MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

What parameters does schema_actionflow accept? +

schema_actionflow accepts 12 parameters: op, name, type, items, names, nodeId, appExId, isAsync, newName, timeout, arrayLevel, displayName. Required: op. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on schema_actionflow? +

Register the Zion MCP server in PolicyLayer and add a rule for schema_actionflow: 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.

What risk level is schema_actionflow? +

schema_actionflow is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit schema_actionflow? +

Yes. Add a rate_limit block to the schema_actionflow 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.

How do I block schema_actionflow completely? +

Set action: deny in the PolicyLayer policy for schema_actionflow. 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.

What MCP server provides schema_actionflow? +

schema_actionflow 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.