input

Skill input

SERVEROpenClaw SOURCEopenclaw

Low RISK CLASS

Category Other

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity verified Pull the record →

This record as markdown: /tools/openclaw/input.md

WHAT IT DOES

What input does on OpenClaw

AI agents call input as a supporting operation in OpenClaw workflows.

RISK

Why input is rated Low

The name and description ('Skill input') provide no meaningful detail about what action this tool performs. It could be providing input to a skill/workflow, but without more context it is impossible to determine if it reads, writes, executes, or does something else. Defaulting to Other with low confidence due to insufficient information.

From the tool's definition Tool name is 'input' and description is 'Skill input' — both are uninformative about what the tool actually does.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs input safely

PolicyLayer is an MCP gateway: it sits between your AI agents and OpenClaw, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For input, this is the rule to start with:

input Rate-limited

input gets a rate cap, and everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "input": {
      "limits": [
        {
          "counter": "input_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

SET A RULE FOR THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect OpenClaw, apply this rule, and every input call is checked against it from then on.

FAQ

Questions about input

What does the input tool do? +

Skill input. It is categorised as a Other tool in the OpenClaw MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on input? +

Register the OpenClaw MCP server in PolicyLayer and add a rule for 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 OpenClaw. Nothing to install.

What risk level is input? +

input is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit input? +

Yes. Add a rate_limit block to the 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.

How do I block input completely? +

Set action: deny in the PolicyLayer policy for 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.

What MCP server provides input? +

input is provided by the OpenClaw MCP server (openclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on OpenClaw, and thousands of servers like it.

This server

All 129 OpenClaw tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Tool risk categories →MCP tool →