Reset a project. IRREVERSIBLE: requires a human to approve a native GUI dialog by retyping the project id; the agent cannot self-approve. Set MCP_HITL=off to fall back to the confirmProjectExId/force text gate in headless automation.
AI agents call reset_project 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
force | boolean | — | |
projectExId | string | Yes | |
languageType | string | — | |
confirmProjectExId | string | — |
Parameters from the server's own tool schema.
Reset operations that are irreversible destroy or overwrite existing project data and cannot be undone. While the tool includes a human-approval gate (MCP_HITL) that reduces immediate misuse risk, the underlying capability remains destructive.
From the tool's definition 'Reset a project. IRREVERSIBLE' – the description explicitly states this action is irreversible, which is the defining characteristic of destructive operations. The tool clears or reinitializes project state without recovery options.
Attacks that exploit this kind of access
Reset a project. IRREVERSIBLE: requires a human to approve a native GUI dialog by retyping the project id; the agent cannot self-approve. Set MCP_HITL=off to fall back to the confirmProjectExId/force text gate in headless automation. 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.
reset_project accepts 4 parameters: force, projectExId, languageType, confirmProjectExId. Required: projectExId. 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 reset_project: 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.
reset_project is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the reset_project 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 reset_project. 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.
reset_project 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 →