set_autonomy_level

A execute tool on the Kiln MCP server.

SERVERKiln SOURCEcodeofaxel/Kiln

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/kiln/set-autonomy-level.md

WHAT IT DOES

What set_autonomy_level does on Kiln

AI agents invoke set_autonomy_level to trigger actions in Kiln. 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.

RISK

Why set_autonomy_level is rated High

On a 3D printer control server, setting an autonomy level likely controls how much independent decision-making an AI agent can perform over physical hardware. This is an Execute-class action (triggering external/physical operations) with potentially high blast radius if an agent is granted elevated autonomy over printers. Confidence is lowered due to the empty description.

From the tool's definition Tool name 'set_autonomy_level' on a server that provides 'AI agent control of 3D printers'. Description is empty and uninformative.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs set_autonomy_level safely

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

set_autonomy_level Rate-limited

set_autonomy_level 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "set_autonomy_level": {
      "limits": [
        {
          "counter": "set_autonomy_level_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about set_autonomy_level

What does the set_autonomy_level tool do? +

set_autonomy_level is a execute tool on the Kiln MCP server. It is categorised as a Execute tool in the Kiln MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on set_autonomy_level? +

Register the Kiln MCP server in PolicyLayer and add a rule for set_autonomy_level: 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 Kiln. Nothing to install.

What risk level is set_autonomy_level? +

set_autonomy_level is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit set_autonomy_level? +

Yes. Add a rate_limit block to the set_autonomy_level 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 set_autonomy_level completely? +

Set action: deny in the PolicyLayer policy for set_autonomy_level. 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 set_autonomy_level? +

set_autonomy_level is provided by the Kiln MCP server (codeofaxel/Kiln). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Kiln, and thousands of servers like it.

This server

All 402 Kiln tools → High-risk tools on this server →

Across the catalogue

set_breakpoint on Frida Game Hacking MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →