MaxEllis/orcaslicer-mcp

Let Claude work alongside you in a real, running OrcaSlicer. It loads models, arranges the plate, tunes settings, slices, and reads the result back as numbers you can question: which feature ate the print time, what a setting actually does, whether a profile breaks your printer's physics. Every change lands in the GUI while you watch, so the slicer stays yours and you get better at it as you go.
This package is an MCP server: it bundles no model. It talks to OrcaSlicer, at an address you configure (localhost by default), and, when you use the printer tools, makes read-only requests to your 3D printer. It sends the printer no commands and uploads nothing to it. The model comes from your MCP client. If that client uses a hosted one, your conversation goes there as any chat does; your models, profiles, and gcode stay on the machine running the slicer. Point the client at a local model and nothing goes to a hosted service.
What it can do
Knowing what the settings mean
An offline settings reference ships with the package, carrying the authoritative label, tooltip, type, range, enum, and default for each key, so describe_setting, search_settings, and compare_settings answer from OrcaSlicer's own source instead of guessing. consult composes curated slicing knowledge and your saved notes by topic, symptom, or goal.
check_profile_physics is a deterministic gate. It overlays proposed changes on the live config, runs flow, temperature, geometry, and cooling math, then returns ok, warnings, or blocked. Accelerations your printer cannot reach and speeds past the flow ceiling get caught before they reach a print.
Settings
Read and write any of roughly 800 OrcaSlicer settings on the live config, for the whole plate or scoped narrower: get_config, set_config, find_config_keys, set_layer_height, set_height_range for a band of layers, and set_object_config for one object's overrides.
On a multi-filament setup, per-filament keys are read merged across every loaded slot but written one preset at a time, and selecting a preset discards unsaved overrides in every group. So make filament edits first and print edits second; docs/order-of-operations.md explains why and gives the sequence.
Presets
list_presets, select_preset, get_preset_config, edit_preset, save_preset, rename_preset, delete_preset. select_preset discards unsaved overrides in every group, not only the one switched; see docs/order-of-operations.md.
Slicing, and reading the result back
slice, slice_and_wait, apply_and_slice, cancel_slice, get_slice_status, get_slice_warnings, get_gcode.
get_slice_breakdown returns per-feature time, filament, and flow. OrcaSlicer shows the same information in the legend beside its preview, sized for a screen; this returns it as numbers an assistant can compare and act on:
It answers which feature is eating the time without slicing repeatedly to find out. A prediction_check rides along and flags any role where the profile's requested speed got throttled at the flow ceiling.
compare_slices slices the current plate under several named variants and returns one comparison, so "what does layer height actually cost me?" is a single question rather than four manual slices. It applies each variant over your original config, restores it when done, and hands back a verdict plus a table with every delta already worked out:
It only crowns a winner when one variant genuinely beats the rest on time, filament, and warnings; when they trade off, it names the fastest, the lightest, and where the warnings landed, and leaves the choice in front of you. Pass detail=True for the per-feature split of each variant.
Models and the plate
load_model (.stl, .obj, .3mf, plus .step and .stp on fork v2.3.2-mcp.3 and later), list_objects with each object's world-space bounding box and an on_plate flag, transform_object, duplicate_object, delete_object, arrange_plate, auto_orient, check_placement, diagnose_plate, get_job_status.
Several plates
list_plates, add_plate, select_plate, delete_plate and move_object_to_plate build a multi-plate project the way the toolbar does: one part per plate, each sliced on its own. Slicing, G-code, renders and job status always act on the current plate, so select a plate before you slice it. list_objects reports the plate each object sits on. Keep arrange_plate away from a layout like this: OrcaSlicer's arrange packs every unlocked plate together again. These need fork v2.4.2-mcp.13 or later.