Action-flow nodes (addressed by actionFlowId + nodeId; ids from schema_actionflow op=GET_DETAIL). Fill node value bindings with schema_create_binding and conditions with schema_condition_expr. Changes apply immediately; use schema_undo to revert the last change. Ops: - op=ADD_BRANCH_ITEM → ADD_AC...
AI agents use schema_actionflow_node 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 | |
name | string | — | |
node | object | — | |
config | object | — | |
nodeId | string | — | |
appExId | string | null | — | |
newName | string | — | |
nodeIds | array | — | |
oldName | string | — | |
schemaPath | array | — | |
afterNodeId | string | — | |
displayName | string | — |
Parameters from the server's own tool schema.
This tool creates and modifies action flow nodes, branches, and bindings in a project schema. Changes are immediately applied but are reversible via schema_undo, placing it in the Write category. The high severity reflects that misconfigured action flows could break application logic across the entire project.
From the tool's definition ADD_ACTION_FLOW_NODE, ADD_ACTION_FLOW_BRANCH_ITEM, ADD_CUSTOM_CODE_NODE_INPUT, ADD_GLOBAL_VARIABLES_NODE_TARGETS — operations that add/modify nodes and bindings in action flows; 'Changes apply immediately; use schema_undo to revert the last change'
Risk signalsHigh parameter count (17 properties)
Attacks that exploit this kind of access
Action-flow nodes (addressed by actionFlowId + nodeId; ids from schema_actionflow op=GET_DETAIL). Fill node value bindings with schema_create_binding and conditions with schema_condition_expr. Changes apply immediately; use schema_undo to revert the last change. Ops: - op=ADD_BRANCH_ITEM → ADD_ACTION_FLOW_BRANCH_ITEM (req: actionFlowId, branchSeparationId) - op=ADD_NODE → ADD_ACTION_FLOW_NODE (req: actionFlowId, afterNodeId, node) - op=ADD_CODE_INPUT → ADD_CUSTOM_CODE_NODE_INPUT (req: actionFlowId, name, nodeId) - op=ADD_VAR_TARGETS → ADD_GLOBAL_VARIABLES_NODE_TARGETS (req: actionFlowId, nodeId, variableKeys) - op=DELETE_NODES → DELETE_ACTION_FLOW_NODES (req: actionFlowId, nodeIds) - op=DELETE_CODE_INPUT → DELETE_CUSTOM_CODE_NODE_INPUT (req: actionFlowId, name, nodeId) - op=DELETE_VAR_TARGETS → DELETE_GLOBAL_VARIABLES_NODE_TARGETS (req: actionFlowId, nodeId, variableKeys) - op=CONTEXT_INFO → GET_ACTION_FLOW_CONTEXT_INFO (req: schemaPath) - op=MOVE_NODE → MOVE_ACTION_FLOW_NODE (req: actionFlowId, afterNodeId, nodeId) - op=RENAME_CODE_INPUT → RENAME_CUSTOM_CODE_NODE_INPUT (req: actionFlowId, newName, nodeId, oldName) - op=UPDATE_NODE → UPDATE_ACTION_FLOW_NODE (req: actionFlowId, nodeId). 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_actionflow_node accepts 12 parameters: op, name, node, config, nodeId, appExId, newName, nodeIds, oldName, schemaPath, afterNodeId, displayName. 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_actionflow_node: 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_actionflow_node 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_actionflow_node 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_actionflow_node. 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_actionflow_node 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 →