This record as markdown: /tools/247arjun-mcp-curl/curl-delete.md
What curl_delete does on Curl MCP Server
AI agents call curl_delete to permanently remove resources in Curl MCP Server, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why curl_delete is rated Critical
HTTP DELETE requests are inherently destructive operations that remove data from remote systems. While the actual impact depends on what server endpoint is targeted, the tool's explicit purpose is to delete resources. Combined with the curl capability to target arbitrary URLs, this tool could irreversibly delete data on any accessible HTTP service.
From the tool's definition Tool name is 'curl_delete' and description states 'Make an HTTP DELETE request using curl'. HTTP DELETE requests are designed to delete resources on remote servers.
Attacks that exploit this kind of access
The rule that runs curl_delete safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Curl MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For curl_delete, this is the rule to start with:
curl_delete is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Curl MCP Server, apply this rule, and every curl_delete call is checked against it from then on.
Questions about curl_delete
Make an HTTP DELETE request using curl. It is categorised as a Destructive tool in the Curl MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Curl MCP Server MCP server in PolicyLayer and add a rule for curl_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 Curl MCP Server. Nothing to install.
curl_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 curl_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 curl_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.
curl_delete is provided by the Curl MCP Server MCP server (247arjun/mcp-curl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Curl MCP Server, and thousands of servers like it.
Across the catalogue