Make an HTTP DELETE request to a specified URL with optional headers. Supports secret substitution using {secrets.key} syntax in URL and headers where 'key' corresponds to HAL_SECRET_KEY environment variables.
Risk signalsAccepts URL/endpoint input (url)
Part of the Hal server.
Free to start. No card required.
AI agents may call http-delete to permanently remove or destroy resources in Hal. 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 http-delete in a loop, permanently destroying resources in Hal. 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": [
"http-delete"
]
}See the full Hal policy for all 8 tools.
These attack patterns abuse exactly the kind of access http-delete 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.
Make an HTTP DELETE request to a specified URL with optional headers. Supports secret substitution using {secrets.key} syntax in URL and headers where 'key' corresponds to HAL_SECRET_KEY environment variables.. It is categorised as a Destructive tool in the Hal MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Hal MCP server in PolicyLayer and add a rule for http-delete: 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 Hal. Nothing to install.
http-delete 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 http-delete 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 http-delete. 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.
http-delete is provided by the Hal MCP server (hal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Hal 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.