Run a curl command against the given target with the provided options.
AI agents invoke run_curl_tool to trigger actions in pentestMCP. 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.
This tool permits execution of arbitrary curl commands against attacker-specified targets. Curl is a powerful utility capable of making HTTP requests, downloading files, uploading data, and interacting with APIs. An AI agent given this tool could exfiltrate data, interact with internal services, perform reconnaissance, or pivot through the network depending on the curl arguments provided.
From the tool's definition 'Run a curl command against the given target with the provided options' — executes arbitrary curl commands which can perform network operations, data exfiltration, request manipulation, and interact with external systems based on agent-controlled arguments.
Documented attack patterns abuse exactly the kind of access run_curl_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and pentestMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for run_curl_tool:
{
"version": "1",
"default": "deny",
"tools": {
"run_curl_tool": {
"limits": [
{
"counter": "run_curl_tool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_curl_tool 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.
Run a curl command against the given target with the provided options. It is categorised as a Execute tool in the pentestMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the pentest MCP server in PolicyLayer and add a rule for run_curl_tool: 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 pentestMCP. Nothing to install.
run_curl_tool 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 run_curl_tool 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 run_curl_tool. 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.
run_curl_tool is provided by the pentest MCP server (ramkansal/pentestmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 36 pentestMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
36 pentestMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.