Skip to main content
Glama
creator5-slicer-mcp

creator5-slicer-mcp

by rsutcliffe

slice_model

Slices 3D models for the Flashforge Creator 5 using filament and purpose settings, returning a 3MF project, G-code, print time, filament estimates, applied settings, and warnings.

Instructions

Slice a model for the Creator 5 with settings chosen for the filament and purpose.

Returns a project file (project_3mf) to open in the slicer and print from, the G-code path, print time, filament use, the settings applied with reasons, and any warnings to pass on to the user.

Args: model_path: Absolute path to an STL, 3MF, STEP or OBJ file on this computer. filament: Filament as the user describes it, e.g. "black PLA", "PETG", "TPU 95A". quality: draft, standard or fine. strength: decorative, standard, functional or structural. nozzle: Nozzle diameter in mm: 0.25, 0.4, 0.6 or 0.8. supports: auto, on or off. brim: auto, on or off. layer_height: Exact layer height in mm, or 0 to let quality decide. precise_fit: True for parts that must mate with other parts. smooth_top: True to iron flat top surfaces. copies: Number of copies to arrange on the plate. auto_orient: Let the slicer rotate the part. Leave False when the model is already oriented for strength. process_overrides: Extra OrcaSlicer process settings applied last, e.g. {"wall_loops": 5}. filament_overrides: Extra OrcaSlicer filament settings, e.g. {"nozzle_temperature": 215}. job_name: Name for the output folder and files. pro: True for the Creator 5 Pro. nozzle_temp: Nozzle temperature in C from the spool's label, or 0 to use the preset. bed_temp: Bed temperature in C from the spool's label, or 0 to use the preset. max_speed: Fastest print speed in mm/s the spool's label recommends, or 0 for no extra limit.

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": {
      "model_path": "<model_path>",
      "filament": "<filament>"
    },
    "name": "slice_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
proNo
brimNoauto
copiesNo
nozzleNo0.4
qualityNostandard
bed_tempNo
filamentYes
job_nameNo
strengthNostandard
supportsNoauto
max_speedNo
model_pathYes
smooth_topNo
auto_orientNo
nozzle_tempNo
precise_fitNo
layer_heightNo
process_overridesNo
filament_overridesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden, and it does substantial work: it discloses the return payload (project 3MF, G-code path, print time, filament use, applied settings with reasons, and warnings). The "0 to let the preset decide" conventions on layer_height, nozzle_temp, bed_temp and max_speed convey real behavioral nuance. It stops short of disclosing side effects such as writing files/folders to disk or likely runtime, which matters for a slicing operation.

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?

Structure is front-loaded correctly: purpose first, return payload second, then a terse argument list. The length is justified by 19 undocumented parameters, and each bullet earns its place. Slight looseness in the returns sentence, which packs six outputs into one run-on line, keeps it from a 5.

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 complex, high-parameter tool with no annotations and no output schema, the definition covers purpose, inputs, defaults and return values well enough to call it correctly. Remaining omissions are operational rather than invocation-critical: expected runtime, disk/network prerequisites, failure behavior, and whether the slicer must be installed locally.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate, and it does: all 19 parameters are explained in plain language with allowed values inlined (draft/standard/fine, decorative/standard/functional/structural, auto/on/off, nozzle diameters, accepted model formats). It also adds intent-level meaning beyond the schema, e.g. precise_fit for mating parts, auto_orient to leave False for already-oriented parts, and overrides applied last. The only minor gap is that override key vocabularies are shown by example only.

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

Purpose4/5

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

The opening sentence gives a specific verb and resource ("Slice a model") plus the target hardware (Creator 5) and the basis for settings (filament and purpose). It also implicitly separates itself from open_in_slicer and send_to_printer by stating it returns a project file "to open in the slicer and print from" rather than performing those actions. It never explicitly names a sibling such as recommend_settings, so the boundary with that tool must be inferred.

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

Usage Guidelines3/5

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

Guidance is implied rather than stated: the description makes clear this is the step that turns a model file into printable output, which is enough to infer the use case. There is no explicit when-to-use/when-not-to-use, no statement of prerequisites (e.g. checking setup first), and no routing to alternatives for setting selection or printer submission.

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