# run_benchmark

A execute tool on the Kiln MCP server.

Agent View of the PolicyLayer registry record for `run_benchmark`. HTML page: https://policylayer.com/tools/kiln/run-benchmark

## Facts

- Tool: `run_benchmark`
- Server: Kiln (`codeofaxel/Kiln`) — https://policylayer.com/tools/kiln.md
- Homepage: https://github.com/codeofaxel/Kiln
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run_benchmark",
    "arguments": {}
  }
}
```

## Why run_benchmark is rated High

The 'run' verb combined with 'benchmark' indicates code/command execution rather than data retrieval or modification. Benchmarking typically involves triggering hardware diagnostics, stress tests, or performance measurements on the printer device. While the empty description creates some ambiguity, the pattern fits Execute (commands with external side effects) rather than Read, Write, or Destructive.

From the tool's own definition: "Tool named 'run_benchmark' with no description provided. Given the server context (3D printer control via OctoPrint, Moonraker, Bambu, Prusa, Elegoo), 'run_benchmark' most likely executes performance tests or diagnostics on printer hardware/firmware,…"

## Use case

AI agents invoke run_benchmark 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Kiln:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_benchmark": {
      "limits": [
        {
          "counter": "run_benchmark_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Kiln (401)

- `cancel_print` — Destructive — https://policylayer.com/tools/kiln/cancel-print.md
- `cancel_print_recovery` — Destructive — https://policylayer.com/tools/kiln/cancel-print-recovery.md
- `cancel_print_service_order` — Destructive — https://policylayer.com/tools/kiln/cancel-print-service-order.md
- `cancel_split_plan` — Destructive — https://policylayer.com/tools/kiln/cancel-split-plan.md
- `delete_agent_note` — Destructive — https://policylayer.com/tools/kiln/delete-agent-note.md
- `delete_cached_model` — Destructive — https://policylayer.com/tools/kiln/delete-cached-model.md
- `delete_file` — Destructive — https://policylayer.com/tools/kiln/delete-file.md
- `delete_shipping_profile` — Destructive — https://policylayer.com/tools/kiln/delete-shipping-profile.md
- `fulfillment_cancel` — Destructive — https://policylayer.com/tools/kiln/fulfillment-cancel.md
- `remove_mesh_floating_regions` — Destructive — https://policylayer.com/tools/kiln/remove-mesh-floating-regions.md
- `remove_spool` — Destructive — https://policylayer.com/tools/kiln/remove-spool.md
- `rollback_design_version` — Destructive — https://policylayer.com/tools/kiln/rollback-design-version.md
- `rollback_firmware` — Destructive — https://policylayer.com/tools/kiln/rollback-firmware.md
- `untrust_printer` — Destructive — https://policylayer.com/tools/kiln/untrust-printer.md
- `acquire_printer_lock` — Execute — https://policylayer.com/tools/kiln/acquire-printer-lock.md
- `arrange_parts_on_plate` — Execute — https://policylayer.com/tools/kiln/arrange-parts-on-plate.md
- `auto_arrange_parts_on_plate` — Execute — https://policylayer.com/tools/kiln/auto-arrange-parts-on-plate.md
- `auto_orient_model` — Execute — https://policylayer.com/tools/kiln/auto-orient-model.md
- `await_print_completion` — Execute — https://policylayer.com/tools/kiln/await-print-completion.md
- `boolean_mesh_op` — Execute — https://policylayer.com/tools/kiln/boolean-mesh-op.md
- `calibrate_direct` — Execute — https://policylayer.com/tools/kiln/calibrate-direct.md
- `clear_emergency_stop` — Execute — https://policylayer.com/tools/kiln/clear-emergency-stop.md
- `compile_scad` — Execute — https://policylayer.com/tools/kiln/compile-scad.md
- `complete_print_recovery` — Execute — https://policylayer.com/tools/kiln/complete-print-recovery.md
- `confirm_print_recovery` — Execute — https://policylayer.com/tools/kiln/confirm-print-recovery.md
- `design_to_gcode_pipeline` — Execute — https://policylayer.com/tools/kiln/design-to-gcode-pipeline.md
- `emergency_stop` — Execute — https://policylayer.com/tools/kiln/emergency-stop.md
- `emergency_trip_input` — Execute — https://policylayer.com/tools/kiln/emergency-trip-input.md
- `firmware_resume_print` — Execute — https://policylayer.com/tools/kiln/firmware-resume-print.md
- `force_print_oversize` — Execute — https://policylayer.com/tools/kiln/force-print-oversize.md
- …and 371 more: https://policylayer.com/tools/kiln.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=kiln · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/kiln