Skip to main content
Glama
Anycubic Slicer MCP

Anycubic Slicer MCP

Plan a multi-part project

plan_project

Plans multi-part 3D print projects from a folder or .zip by finding models, orienting each part, packing them onto plates, and returning time/filament estimates plus blocking questions.

Instructions

Plan a whole multi-part project from a folder or .zip: find every model, lay each in its best orientation and pack them onto plates.

Reads counts from names like clip_x4.stl and from READMEs. Returns plates with rough time and filament, stated assumptions, and questions about anything unclear (duplicate versions, odd scale, parts too big, missing counts, colours, grouping). Put the blocking questions to the user, then call again with plan_id and the answers; part ids are paths relative to the project folder. Slicing happens only in slice_project. Saves the plan, and unpacks zips, under the server's state folder; each call without plan_id starts a new plan.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
goalNo'fewest_plates' or 'by_colour' (one colour per plate).
pathNoFolder, .zip, or single model file of the project. Required unless plan_id is given.
scalesNoScale per part id, e.g. {'bracket.stl': 25.4} for a part exported in inches.
coloursNoColour per part id, e.g. {'knob.stl': 'red'}, used by goal='by_colour'.
excludeNoPart ids to leave out.
includeNoPart ids to put back in, such as test pieces left out by default.
plan_idNoRe-plan an earlier plan with new answers; earlier answers are kept.
printerNoPrinter preset name or a unique part of it, e.g. 'Kobra X'. Omit to use the printer selected in the slicer window.
processNoProcess preset (layer height, speeds), e.g. '0.20mm Standard'. Omit to use the slicer window's selection.
answeredNoQuestion ids the user settled by keeping the suggested default.
filamentsNoFilament preset names, one per filament slot, e.g. ['Anycubic PLA']. Omit to use the slicer window's selection.
overridesNoSetting overrides applied to every plate, as for slice_model.
quantitiesNoCopies per part id, e.g. {'clip.stl': 4}.
spacing_mmNoGap between parts on a plate in mm, 1 to 50. Default 6.
separate_supportedNoTrue puts parts that need supports on their own plates.
max_hours_per_plateNoKeep each plate under this many hours (rough estimate), 0.25 to 200.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false and idempotentHint=false, and the description earns the credit by explaining why: saves the plan and unpacks zips into the server's state folder, and each call without plan_id is a brand-new plan. It further discloses the return payload (plates with rough time and filament, stated assumptions, clarifying questions), which the annotations cannot convey.

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?

Content is front-loaded and dense with useful information, with only mild redundancy (the state-folder/new-plan sentence is tacked onto the end and reads awkwardly). Every sentence carries information an agent needs, but the ordering could be tighter.

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 16-parameter tool with no output schema, the description covers the input-driven workflow, the side effects (state folder, zip unpacking), and the shape of the response including the questions that must be routed to the user. Nothing essential for correct invocation is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning the schema lacks: part ids are "paths relative to the project folder", and plan_id/answers form a re-plan loop where earlier answers are retained. That resolves the ambiguous "part id" terminology used across scales, colours, exclude, include, and quantities.

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?

"Plan a whole multi-part project from a folder or .zip" gives a specific verb and resource, and the follow-up clause enumerates the concrete operations (find models, orient, pack onto plates). It also explicitly delegates slicing to the sibling slice_project, so the boundary is unambiguous.

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 prescribes the interaction loop: read the blocking questions, put them to the user, then call again with plan_id and the answers. It also states the exclusion against slice_project ("Slicing happens only in slice_project") and clarifies that a call without plan_id starts a fresh plan, which tells the agent when to start over vs. continue.

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