AI agents invoke send_input to trigger actions in Pentest 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.
This tool sends input to interactive sessions on a penetration testing server capable of running Metasploit, reverse shells, and arbitrary commands via SSH on Linux systems. Sending input to such sessions can trigger arbitrary code execution, exploitation of vulnerabilities, or destructive operations depending on what is running in the session.
From the tool's definition Send input to an interactive session' on a server that supports 'Metasploit, reverse shells, and complex multi-step security workflows' via persistent tmux sessions
Documented attack patterns abuse exactly the kind of access send_input gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pentest MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for send_input:
{
"version": "1",
"default": "deny",
"tools": {
"send_input": {
"limits": [
{
"counter": "send_input_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}send_input 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.
Send input to an interactive session. It is categorised as a Execute tool in the Pentest MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pentest MCP Server MCP server in PolicyLayer and add a rule for send_input: 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 Pentest MCP Server. Nothing to install.
send_input 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 send_input 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 send_input. 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.
send_input is provided by the Pentest MCP Server MCP server (layesec006/pentest-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pentest 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.
12 Pentest MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.