Get the value submitted by the user after show_input_form was called. This tool uses LONG-POLLING: it will BLOCK and wait until the user submits or cancels the input, then return the result. Returns status: submitted (with value), cancelled, or idle (no input was requested).
AI agents call get_user_input to retrieve information from Pane without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a blocking read operation that polls for and retrieves user-submitted form data. While it blocks execution flow, it performs no side effects, creates no data, executes no code, and deletes nothing. It is purely a data retrieval mechanism for input that the user has already voluntarily submitted. The blocking behavior affects agent flow but not system state.
From the tool's definition Tool retrieves user input that was previously submitted via show_input_form; described as returning status (submitted/cancelled/idle) with optional value. No modification, deletion, or execution occurs.
Documented attack patterns abuse exactly the kind of access get_user_input gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pane, and nothing reaches the server without passing your rules. This is the rule we recommend for get_user_input:
{
"version": "1",
"default": "deny",
"tools": {
"get_user_input": {}
}
}get_user_input is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the value submitted by the user after show_input_form was called. This tool uses LONG-POLLING: it will BLOCK and wait until the user submits or cancels the input, then return the result. Returns status: submitted (with value), cancelled, or idle (no input was requested). It is categorised as a Read tool in the Pane MCP Server, which means it retrieves data without modifying state.
Register the Pane MCP server in PolicyLayer and add a rule for get_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 Pane. Nothing to install.
get_user_input is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_user_input is provided by the Pane MCP server (zabaca/pane). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pane, 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.
15 Pane tools catalogued and risk-classified — across an index of 43,000+ MCP servers.