AI agents invoke ztype_tool_calls to trigger actions in Zion. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
appExId | string | null | — | |
verbose | boolean | — | |
toolCalls | array | Yes | |
projectExId | string | — | |
appVersionExId | string | null | — |
Parameters from the server's own tool schema.
This tool executes ztype Copilot operations against a schema with immediate application of patches. While the description doesn't explicitly say it can delete or overwrite, the ability to 'run' arbitrary tool calls and apply patches immediately qualifies it as Execute rather than Write, since the exact effects are contingent on the ztype tool calls invoked and their implementation details are opaque from this…
From the tool's definition Tool description states 'Run ztype Copilot tool calls against the loaded schema. Any resulting CRDT patch is applied immediately'.
Attacks that exploit this kind of access
Run ztype Copilot tool calls against the loaded schema. Any resulting CRDT patch is applied immediately; use schema_undo to revert the last change. It is categorised as a Execute tool in the Zion MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
ztype_tool_calls accepts 5 parameters: appExId, verbose, toolCalls, projectExId, appVersionExId. Required: toolCalls. 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 ztype_tool_calls: 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.
ztype_tool_calls is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ztype_tool_calls 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 ztype_tool_calls. 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.
ztype_tool_calls 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 →