Use after explicit user intent to unpublish a Dreamlit workflow. Side effect: disables live triggers or schedules for that workflow and stops future automated sends. Returns updated workflow status and app URLs. Do not use for deleting drafts, canceling one broadcast run, or editing workflow cont...
Part of the Dreamlit server.
Free to start. No card required.
AI agents may call unpublish_workflow to permanently remove or destroy resources in Dreamlit. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call unpublish_workflow in a loop, permanently destroying resources in Dreamlit. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"unpublish_workflow"
]
}See the full Dreamlit policy for all 11 tools.
These attack patterns abuse exactly the kind of access unpublish_workflow gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Use after explicit user intent to unpublish a Dreamlit workflow. Side effect: disables live triggers or schedules for that workflow and stops future automated sends. Returns updated workflow status and app URLs. Do not use for deleting drafts, canceling one broadcast run, or editing workflow content.. It is categorised as a Destructive tool in the Dreamlit MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Dreamlit MCP server in PolicyLayer and add a rule for unpublish_workflow: 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 Dreamlit. Nothing to install.
unpublish_workflow 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 unpublish_workflow 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 unpublish_workflow. 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.
unpublish_workflow is provided by the Dreamlit MCP server (https://mcp.dreamlit.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Dreamlit tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.