Skip to main content
Glama
Anycubic Slicer MCP

Anycubic Slicer MCP

Save a user preset

save_user_preset
DestructiveIdempotent

Save a new process, filament, or printer preset to Anycubic Slicer Next user presets so settings persist for future prints; use slice_model overrides for one-off prints instead.

Instructions

Write a new process, filament or printer preset into the user's Anycubic Slicer Next presets.

Use it when the user wants settings kept for future prints; for a one-off print pass overrides to slice_model instead, and for fixing a failed print use diagnose_print first (which only suggests changes and saves nothing). Writes one JSON file to the slicer's user preset folder; with overwrite=true it replaces an existing one. Ask the user before calling. The slicer window shows it after a restart. Returns {saved, kind, inherits}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>",
      "name": "<name>",
      "inherits": "<inherits>",
      "settings": "<settings>"
    },
    "name": "save_user_preset"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes'process', 'filament' or 'machine'.
nameYesName for the new preset as it will appear in the slicer, 1-120 characters, no <>:"/\|?*;
printerNoLimit the new process/filament preset to this printer. Omit to keep the parent's printers.
inheritsYesExisting preset to start from; the new preset stores only what differs.
settingsYesSetting key to value, only the values that differ, e.g. {'wall_loops': 3}. Find keys with get_preset.
overwriteNoReplace an existing user preset with the same name. Default false refuses.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.3.1
    • addedInput schema / properties / inherits / description
      Added value: +"Existing preset to start from; the new preset stores only what differs."
    • addedInput schema / properties / kind / description
      Added value: +"'process', 'filament' or 'machine'."
    • addedInput schema / properties / name / description
      Added value: +"Name for the new preset as it will appear in the slicer, 1-120 characters, no <>:\"/\\|?*;"
    • addedInput schema / properties / overwrite
      Added value: +{
      +  "default": false,
      +  "description": "Replace an existing user preset with the same name. Default false refuses.",
      +  "title": "Overwrite",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / printer
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Limit the new process/filament preset to this printer. Omit to keep the parent's printers.",
      +  "title": "Printer"
      +}
    • addedInput schema / properties / settings / description
      Added value: +"Setting key to value, only the values that differ, e.g. {'wall_loops': 3}. Find keys with get_preset."
  2. First observedv0.3.0

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (destructiveHint=true, idempotentHint=true, readOnlyHint=false), the description discloses the concrete write footprint (one JSON file in the user preset folder), what overwrite destroys (an existing preset with the same name), that the change is not visible until a slicer restart, and a required user confirmation. With no output schema, it also states the return shape {saved, kind, inherits}. The gaps are error paths, e.g. a missing or invalid 'inherits' preset, which are left unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The structure is front-loaded and purposeful: purpose first, then routing guidance, then mechanics, then the return shape. Each sentence carries information, though the preset-path and restart details could be compressed slightly and the opening verb list partially duplicates the kind parameter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, 6-parameter write tool with a nested settings object and no output schema, the definition covers the essentials: write target, overwrite semantics, confirmation, restart visibility, and return fields. It stops short of describing failure behavior (invalid inherits, name collisions when overwrite=false) which matters for a write operation an agent invokes unattended.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter including overwrite, inherits and settings is already documented in structured form. The description restates overwrite's replacement behavior and the diff-only storage of inherits but adds no new syntax, defaults, or format detail beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The definition opens with a specific verb and resource ('Write a new process, filament or printer preset into the user's Anycubic Slicer Next presets') and names the config kinds, so an agent can distinguish it from read-only siblings like list_presets or get_preset without opening the schema. The only nit is that the prose says 'printer' while the schema enum uses 'machine', a trivially resolvable wording mismatch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance ('when the user wants settings kept for future prints') and names two alternatives with the conditions that select them: slice_model for one-off overrides and diagnose_print for failed prints, plus the note that diagnose_print only suggests and saves nothing. It also adds a procedural constraint not found elsewhere: 'Ask the user before calling.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.