AI agents invoke request_user_input to trigger actions in Interactive MCP. 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 appears to execute an operation that requests input from the user, making it an Execute-category tool rather than a simple Read. The lack of a description lowers confidence, but the name and context (sibling tools suggest interactive chat functionality) indicate it triggers external user-facing operations.
From the tool's definition Tool name is 'request_user_input' with no description provided. The name suggests triggering a user interaction or input prompt, which would execute an action to solicit user input.
Documented attack patterns abuse exactly the kind of access request_user_input gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Interactive MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for request_user_input:
{
"version": "1",
"default": "deny",
"tools": {
"request_user_input": {
"limits": [
{
"counter": "request_user_input_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}request_user_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.
request_user_input. It is categorised as a Execute tool in the Interactive MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Interactive MCP server in PolicyLayer and add a rule for request_user_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 Interactive MCP. Nothing to install.
request_user_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 request_user_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 request_user_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.
request_user_input is provided by the Interactive MCP server (ttommyth/interactive-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Interactive MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Interactive MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.