Skip to main content
Glama
Anycubic Slicer MCP

Anycubic Slicer MCP

Slice a planned project

slice_project
Idempotent

Slices each plate from an approved plan into its own G-code and .gcode.3mf files, refusing to run until blocking questions are answered.

Instructions

Slice every plate of a plan from plan_project once the user has approved it.

Refuses while any blocking question is unanswered. Each plate is sliced separately into its own .gcode and .gcode.3mf; parts the slicer can't fit move to the next plate. Takes about as long as slicing each plate, writes the files plus project_summary.json to output_dir (replacing earlier runs), and returns real times and weights per plate, totals, and a preview image of up to six plates.

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": {
      "plan_id": "<plan_id>"
    },
    "name": "slice_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
platesNoOnly slice these plate numbers. Default: all.
plan_idYesPlan id from plan_project.
output_dirNoFolder for the plate files. Default: Documents/Anycubic Slicer MCP/<plan id>.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.1

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations: per-plate file outputs (.gcode and .gcode.3mf), overflow of unfittable parts to the next plate, writes project_summary.json into output_dir and replaces earlier runs, approximate runtime, and the returned payload (per-plate times/weights, totals, preview of up to six plates). The 'replacing earlier runs' note is exactly the kind of side effect an agent needs even when destructiveHint is false.

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?

Front-loads the core action and precondition in the first sentence, then layers side effects and return values. The final sentence is dense with clauses, but no sentence is filler.

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

Completeness5/5

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

For a three-parameter mutation with no output schema, it covers the precondition, per-plate behavior, file/disk side effects with overwrite semantics, runtime expectations, and the shape of the return value. An agent has everything needed to call it and set expectations.

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 plan_id, plates, and output_dir are already documented, and the baseline is 3. The description only lightly reinforces them ('every plate', files plus project_summary.json go to output_dir) without adding format or override semantics beyond the schema.

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?

States a specific verb ('Slice') and resource ('every plate of a plan from plan_project'), plus the gating precondition of user approval. This distinguishes it from slice_model-style single-model tools without needing to open another schema.

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

Usage Guidelines4/5

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

Clearly says when to use it: after the user approves the plan, with plan_id coming from plan_project. It also states a when-not condition ('Refuses while any blocking question is unanswered'). It stops short of naming an explicit alternative for slicing a single model, so it is strong but not exhaustive.

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