Make HTTP requests to web endpoints. Example: GET request to an API or POST data to a server
AI agents invoke curl to trigger actions in IT Tools MCP Server. 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.
curl can send HTTP requests to any endpoint, including internal network resources (SSRF), exfiltrate data, trigger webhooks, or POST sensitive information. It executes external operations whose effects depend entirely on the arguments provided, making it Execute category with high severity due to potential for SSRF, data exfiltration, and triggering unintended server-side actions.
From the tool's definition 'Make HTTP requests to web endpoints' and 'POST data to a server' — executes outbound network requests to arbitrary URLs with arbitrary methods and payloads
Documented attack patterns abuse exactly the kind of access curl gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and IT Tools MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for curl:
{
"version": "1",
"default": "deny",
"tools": {
"curl": {
"limits": [
{
"counter": "curl_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}curl stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Make HTTP requests to web endpoints. Example: GET request to an API or POST data to a server. It is categorised as a Execute tool in the IT Tools MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the IT Tools MCP Server MCP server in PolicyLayer and add a rule for curl: 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 IT Tools MCP Server. Nothing to install.
curl 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 curl 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. 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 is provided by the IT Tools MCP Server MCP server (wrenchpilot/it-tools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from IT Tools MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
119 IT Tools MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.