Slicewise
NPM · @GJLMOTEA/SLICEWISE-MCP
Pre-print checks for Bambu Studio: GUI-faithful CLI slicing, override audit, printability.
Available components
Last scanned (14 hours ago)
Scores higher than 42% of npm servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to gjlmotea/slicewise-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 13 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability59
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 3289 tokens (~205/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage88
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 60% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 8 Nov 26 71
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/@gjlmotea/slicewise-mcp@0.1.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | gjlmotea/slicewise-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/gjlmotea/slicewise-mcp/.github/workflows/release.yml@refs/tags/v0.1.0 |
| Rekor log index | 3748586655 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:b6a7bc33128e1bae6e7d2aab499b7073e163b56ba08bce95989d6abd31df422e6d4825053815ad619c4ab5680bf94789814d2026b51601d39dae2743f |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
bambu_check_printability Check printability ~270
Finds problems visible before slicing: exceeding the build volume, floating bodies that do not touch the plate, an unclosed mesh, the share of steep overhangs, too small a base area, too high an aspect ratio, features that are too thin, and warping risk on large bottom surfaces. Each finding lists the related parameters. Floating detection splits the mesh into shells, merges shells that touch or intersect into bodies, merges shells fully enclosed by another body into it, then checks whether each body reaches the plate and measures the gap to the nearest body: a narrow gap means the parts were not joined in the model (turning on support would make them print as separate pieces); only a wide gap really needs support. Accepts STL, 3MF and OBJ. This is geometric analysis, not a slicing simulation; thin walls inside the model only show up when actually sliced. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| buildVolume | object | – | Defaults to 256×256×256 mm (Bambu Lab P1S / X1C). |
| lineWidthMm | number | – | – |
| modelPath | string | yes | – |
| overhangThresholdDegrees | number | – | Angle from vertical; 0° is a vertical wall, 90° is a horizontal ceiling. Defaults to 45. |
| Name | Type | Req | Description |
|---|---|---|---|
| buildVolume | object | yes | – |
| findings | array | yes | – |
| fitsBuildVolume | boolean | yes | – |
| floatingBodies | array | – | Bodies that do not touch the plate. A gap within 2 mm usually means the parts were not joined during modelling and must be fixed in the modelling software; turning on support would make them print as… |
| inspection | object | yes | – |
| overhangAreaRatio | number | yes | – |
No examples provided.
bambu_compare_presets Compare two presets ~93
Flattens two presets of the same kind and lists the settings that differ. Use it to answer questions like "what exactly is the difference between 0.20 Standard and 0.20 Strength" without reading four levels of JSON by hand. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | yes | – |
| left | string | yes | – |
| limit | integer | – | – |
| right | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| differenceCount | number | yes | – |
| differences | array | yes | – |
| left | string | yes | – |
| right | string | yes | – |
No examples provided.
bambu_compose_model Compose a 3MF with negative / modifier parts ~231
Builds a Bambu project 3MF from a base body STL plus extra parts. A negative part (negative_part) cuts away where it overlaps, a modifier (modifier_part) applies different settings to its region, and support_blocker / support_enforcer control support. In a Bambu model each of these is just one more part with a label, so no geometry (boolean) engine is needed. The output can be read back item by item with bambu_inspect_project, or passed straight to bambu_slice. Writes a file to the output directory.
| Name | Type | Req | Description |
|---|---|---|---|
| baseName | string | – | Display name of the base body part. Defaults to body. |
| basePath | string | yes | Path to the base body STL; it must be inside an allowed model directory. |
| name | string | yes | Output file name (.3mf is appended automatically) and object name. Must not contain path separators. |
| parts | array | yes | – |
| plateCentre | object | – | Where the object lands on the plate. Defaults to the centre of a 256×256 plate (128, 128). |
| Name | Type | Req | Description |
|---|---|---|---|
| byteLength | number | yes | – |
| nextStep | string | yes | – |
| outputPath | string | yes | – |
| parts | array | yes | – |
| warnings | array | yes | – |
No examples provided.
bambu_describe_parameters Explain parameters and their trade-offs ~71
Explains what a parameter does, its unit, its typical range, the cost of raising or lowering it, and related parameters. Call this before changing any parameter, instead of tuning by what merely sounds reasonable. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| group | string | – | – |
| keys | array | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| specs | array | yes | – |
| unknown | array | yes | Keys that are not in the parameter catalog. |
No examples provided.
bambu_diagnose Diagnose a print failure from its symptom ~189
Takes an observed symptom (warping, stringing, layer separation, elephant's foot, holes in the top surface, ...) and returns an ordered list of remedies, each with its mechanism, a suggested value and its cost. Use it when the user describes what went wrong rather than which parameter to change; apply one remedy at a time. If no known symptom matches, it says so instead of guessing. It also points out problems that no parameter can fix. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| material | string | – | The material, e.g. PLA / ABS / PETG / TPU; a material-specific note is returned when one exists. |
| symptom | string | – | The symptom in natural language, e.g. "the bottom layer bulges outward" (elephant's foot). Chinese descriptions are matched too. |
| symptomId | string | – | A known symptom id; skips text matching. |
| Name | Type | Req | Description |
|---|---|---|---|
| available | array | yes | – |
| matched | array | yes | – |
| note | string | – | – |
No examples provided.
bambu_get_status Get Bambu Studio companion status ~71
Reports the BambuStudio data directory, whether the slicer executable is available, preset counts, the machine and filaments currently selected in Studio, the allowed model directories, and the integration level of each model platform. Use it first to see what this server can do on this machine. No side effects.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| allowedModelRoots | array | yes | – |
| catalogs | array | yes | – |
| currentSelection | object | yes | – |
| dataDir | string | yes | – |
| inheritanceFlattening | boolean | yes | – |
| outputConfigured | boolean | yes | – |
| presetCounts | object | yes | – |
| profileId | string | – | – |
| slicerAvailable | boolean | yes | – |
| slicerPath | string | yes | – |
| version | string | yes | – |
No examples provided.
bambu_inspect_model Inspect model geometry ~123
Parses an STL (binary or ASCII), 3MF or OBJ and reports triangle count, bounding box, volume, surface area, and whether the mesh is closed. The format is detected from the file content, not the extension. For 3MF and OBJ it also reports the part count and part list (3MF coordinates have the placement transform applied; OBJ is split into parts by o / g, and Tinkercad's colour export is OBJ). Reads only files inside the allowed directories. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| modelPath | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| boundingBox | object | yes | – |
| closed | boolean | yes | – |
| degenerateTriangles | number | yes | – |
| format | string | – | The format actually detected, based on the content rather than the file extension. |
| openEdges | number | yes | – |
| partCount | number | – | – |
| parts | array | – | – |
| surfaceAreaMm2 | number | yes | – |
| triangleCount | number | yes | – |
| volumeMm3 | number | yes | – |
No examples provided.
bambu_inspect_project Read back the part structure of a 3MF ~110
Reads the objects and parts from a Bambu project 3MF, including each part's subtype and per-part settings. Use it to verify that what was written is really in the file; this is the key advantage of working with files over the GUI: you can compare item by item instead of only looking at the screen. It also flags subtypes that BambuStudio does not recognise. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| projectPath | string | yes | Path to a Bambu project 3MF. |
| Name | Type | Req | Description |
|---|---|---|---|
| objects | array | yes | – |
No examples provided.
bambu_list_presets List presets ~139
Lists machine, process or filament presets. By default only presets selectable in the UI are returned; intermediate presets that exist only to be inherited from (e.g. fdm_process_common) are filtered out. Names listed here do not show real setting values; use bambu_resolve_preset for that. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| includeAbstract | boolean | – | Whether to include intermediate presets that exist only to be inherited from and cannot be selected in the UI. Defaults to false. |
| kind | string | yes | – |
| limit | integer | – | – |
| search | string | – | Filter by a case-insensitive substring of the preset name. |
| Name | Type | Req | Description |
|---|---|---|---|
| entries | array | yes | – |
| kind | string | yes | – |
| returned | number | yes | – |
| total | number | yes | – |
No examples provided.
bambu_measure_clearance Measure clearance between parts ~253
Measures the smallest clearance between the parts in a 3MF or OBJ, to judge whether a print-in-place mechanism will fuse when printed. Parts that touch each other are first merged into rigid bodies before comparing, because Bambu also stores the colour-change segments of a single solid as separate parts; without merging, one piece would be reported as "clearance 0". When the clearance is too small it suggests compensation, distinguishing outer contours from holes (the enclosed side is a hole to the slicer and is controlled by a different parameter). STL has no part boundaries, so it cannot be measured. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| minimumClearanceMm | number | – | The smallest clearance that prints reliably. Defaults to 0.15 (the practical lower limit for PLA with a 0.4 mm nozzle). |
| modelPath | string | yes | Absolute path to a 3MF or OBJ file; it must be inside an allowed model directory. |
| reportThresholdMm | number | – | Part pairs farther apart than this are left out of the report. Defaults to 2 mm. |
| samplingMm | number | – | Surface sampling spacing; smaller is more accurate but slower. Defaults to 0.2 mm. |
| Name | Type | Req | Description |
|---|---|---|---|
| bodies | array | yes | – |
| findings | array | yes | – |
| format | string | yes | – |
| minimumClearanceMm | number | yes | – |
| pairs | array | yes | – |
| partCount | number | yes | – |
| recommendation | object | – | – |
| tightestGapMm | number | – | – |
No examples provided.
bambu_optimize_print_in_place Create a stabilised print-in-place preset ~358
Creates an auto-stabilised copy of the given (or currently selected) process preset that can be used directly in Bambu Studio. Use it when small print-in-place parts detach from the bed or get dragged off by the nozzle. It applies exactly: first-layer outer wall 20 mm/s, first-layer infill 30 mm/s, outer wall capped at 60 mm/s, slowdown for overhangs, avoid crossing printed walls, Monotonic line, and ironing and Fuzzy Skin turned off. If the source is an existing user preset, its leaf-level calibrations (dimensions, elephant's foot, etc.) are kept, but the new file still inherits directly from the system preset. By default Auto Brim is explicitly turned off so the brim does not fuse gear clearances; Brim Ears can be requested explicitly, and you will still be reminded to check the first layer. It does not change filament temperature, cooling or flow, because regular PLA and Silk PLA must be calibrated separately. Writes a file to the user profile directory; takes effect after Bambu Studio is restarted.
| Name | Type | Req | Description |
|---|---|---|---|
| includeBrimEars | boolean | – | Whether to also enable 5 mm Brim Ears. Defaults to false, because the moving clearances must be checked in the first-layer preview first. |
| name | string | – | Name of the new user preset. Defaults to the source preset name with an auto-stabilised suffix appended. |
| overwrite | boolean | – | Whether to replace a preset with the same name if one already exists. Defaults to false. |
| processPreset | string | – | The source process preset; defaults to the one currently selected in Bambu Studio. An existing user preset may be given. |
| Name | Type | Req | Description |
|---|---|---|---|
| basePreset | string | yes | – |
| changes | array | yes | – |
| created | boolean | yes | – |
| manualActions | array | yes | – |
| name | string | yes | – |
| nextStep | string | yes | – |
| overrides | object | yes | Parameters to override; each key is a BambuStudio setting name (e.g. layer_height, sparse_infill_density). |
| overwritten | boolean | yes | – |
| path | string | yes | – |
| preservedKeys | array | yes | – |
| sourcePreset | string | yes | – |
| warnings | array | yes | – |
No examples provided.
bambu_plan_settings Plan settings for a goal ~318
Given what you want (safe and failure-free / fast / strong under load / good surface / economical), returns ordered parameter adjustments grouped by what they counter: adhesion and warping, nozzle collisions, surface quality, structural strength, time, filament. Each move includes its mechanism, a suggested value, its cost, and **the actual value in the current preset and its shape** (per-extruder parameters must be overridden with an array; a scalar is silently not applied). If modelPath is given, a printability analysis runs first and conditional adjustments are added based on the geometry. This is for planning before a print; to work back from a print that already failed, use bambu_diagnose. It only returns a plan and changes nothing. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| filamentPreset | string | – | – |
| goal | string | – | What you want, in natural language, e.g. "don't let it fail, print slowly at high quality" or "in a hurry". Chinese goals are matched too. |
| goalId | string | – | Specify the goal directly; skips text matching. |
| material | string | – | PLA / PETG / ABS / ASA / TPU; a material-specific note is returned when one exists. |
| modelPath | string | – | If a model is given, a printability analysis runs first and conditional adjustments are added based on the geometry (e.g. a wider brim when the base area is too small). |
| processPreset | string | – | Defaults to the preset currently selected in Bambu Studio. |
| Name | Type | Req | Description |
|---|---|---|---|
| available | array | yes | – |
| goal | object | – | – |
| moves | array | yes | – |
| note | string | – | – |
| printability | object | – | – |
No examples provided.
bambu_resolve_preset Flatten a preset inheritance chain ~133
Flattens a preset's inherits chain into the complete settings and records which level each value comes from. A BambuStudio leaf preset usually declares only a few dozen keys and inherits everything else from its parents, so to know the real value of any parameter you must look at the flattened result, not the leaf preset file. Use this whenever you need an actual setting value. No side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| keys | array | – | Return only these parameters. Omit to return all of them (a process preset has about 200 keys). |
| kind | string | yes | – |
| name | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| inheritanceChain | array | yes | The inheritance chain, from the leaf preset to the root. |
| kind | string | yes | – |
| name | string | yes | – |
| origin | string | yes | – |
| provenance | object | yes | Which level of the inheritance chain each key actually comes from. Machine G-code may come from that level's template entry, named like "<preset> template machine_start_gcode". |
| settingCount | number | yes | – |
| settings | object | yes | – |
No examples provided.
bambu_save_user_preset Save a user preset to Bambu Studio ~194
Creates a custom preset that inherits from a system preset, in the BambuStudio user profile directory; it appears in the dropdown after Bambu Studio is restarted. BambuStudio has no plugin API (see bambulab/BambuStudio#9614), so this is the only way to get parameters tuned by an AI into the GUI. Writes a file; an existing preset with the same name is never silently overwritten.
| Name | Type | Req | Description |
|---|---|---|---|
| inherits | string | yes | Name of the system (vendor) preset to inherit from. |
| kind | string | yes | – |
| name | string | yes | Name of the new preset; it appears in the Bambu Studio dropdown. |
| overrides | object | yes | Parameters to override; each key is a BambuStudio setting name (e.g. layer_height, sparse_infill_density). |
| overwrite | boolean | – | Whether to replace an existing preset with the same name. Defaults to false. |
| Name | Type | Req | Description |
|---|---|---|---|
| created | boolean | yes | – |
| nextStep | string | yes | – |
| overwritten | boolean | yes | – |
| path | string | yes | – |
| warnings | array | yes | – |
No examples provided.
bambu_search_models Search for 3D models ~140
Searches for models across platforms. Thingiverse uses its official API (requires THINGIVERSE_TOKEN). MakerWorld and Printables have no official public API, so for them only a search link is returned for a person to open; this is a deliberate downgrade: no scraping or private endpoints pretending to be an API. Do not claim to have searched or downloaded models from those platforms. Does not download any model. Accesses the internet.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| query | string | yes | – |
| sources | array | – | Restrict to these platforms; omit to query all. See catalogs in bambu_get_status for the available values. |
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
| results | array | yes | – |
No examples provided.
bambu_slice Slice (after flattening the inheritance chain) ~275
Slices with the BambuStudio CLI and reports real statistics: layer count, print time, filament weight. Presets are flattened before they are passed to the CLI; feeding the raw presets to the CLI makes every inherited parameter fall back to the built-in default (BambuStudio#1704), so do not call the CLI directly. After slicing, it reads the settings that actually took effect back from the output and audits each override you requested; an overrideAudit entry with honoured = false was not applied. Starts a child process and writes a .gcode.3mf to the configured output directory. It does not send anything to a printer or start a print.
| Name | Type | Req | Description |
|---|---|---|---|
| filamentPresets | array | – | – |
| machinePreset | string | – | – |
| modelPath | string | yes | Absolute path to the model file; it must be inside an allowed model directory. |
| overrides | object | – | Parameters to override; each key is a BambuStudio setting name (e.g. layer_height, sparse_infill_density). |
| placement | object | – | – |
| plate | integer | – | – |
| processPreset | string | – | – |
| reportSettings | array | – | Read back the values these parameters actually took in the output. Use it to confirm the slice really used the preset values rather than the slicer's built-in defaults. |
| Name | Type | Req | Description |
|---|---|---|---|
| appliedSettings | object | – | The actual values in the output of the parameters requested by reportSettings. |
| ok | boolean | yes | – |
| outputPath | string | – | – |
| overrideAudit | array | – | – |
| reason | string | – | – |
| stats | object | – | – |
| stderrTail | array | – | – |
| warnings | array | – | – |
No examples provided.
How do I install the Slicewise MCP server?
Slicewise runs locally as an npm package, launched with npx -y @gjlmotea/slicewise-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @gjlmotea/slicewise-mcp
claude mcp add gjlmotea-slicewise-for-bambu-studio-mcp -- npx -y @gjlmotea/slicewise-mcp
What is the Slicewise MCP server?
Slicewise is an MCP server listed in the public MCP registry as io.github.gjlmotea/slicewise-for-bambu-studio-mcp. Pre-print checks for Bambu Studio: GUI-faithful CLI slicing, override audit, printability. This page covers its npm package (@gjlmotea/slicewise-mcp).
Is the Slicewise MCP server safe to use?
Slicewise scores 71 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Slicewise MCP server expose?
Slicewise exposes 16 tools: bambu_get_status, bambu_list_presets, bambu_resolve_preset, bambu_compare_presets, bambu_describe_parameters, and 11 more. Their descriptions and schemas cost roughly 2,968 tokens of context every time the server is loaded.
Is the Slicewise MCP server still maintained?
Slicewise is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Slicewise MCP server under?
Slicewise declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Slicewise MCP server?
VerifyMCP ran 15 checks on Slicewise, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Slicewise: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.