Skip to main content
Glama

ScanBIM MCP

by io.scanbimlabs

upload_model

Ingest a 3D model from a public URL into APS OSS and kick off a Model Derivative translation job, returning the URN plus a browser viewer link and QR code. Supports 50+ formats: Revit (.rvt/.rfa), Navisworks (.nwd/.nwc), IFC, FBX, OBJ, SolidWorks, point clouds (E57/LAS/RCP), CAD (DWG/STEP/IGES), etc. When to use: you have a publicly downloadable 3D file (S3 presigned URL, GitHub raw, etc.) and need it translated to SVF2 so it can be viewed, measured, or clash-checked via other tools. When NOT to use: the file is only on a local disk or behind auth (fetch will fail) — first push it to a public URL. Do not call to re-translate a model already uploaded; call get_model_metadata instead. APS scopes: data:read data:write data:create bucket:read bucket:create viewables:read Rate limits: APS default ~50 req/min per app per endpoint; Model Derivative translation jobs ~60 req/min; OSS uploads size-limited per file to 100MB for direct upload, larger via resumable. Errors: 401 APS token expired/invalid — refresh; 403 scope or resource permission denied; 404 source file_url not reachable or bucket not found — check the ID; 409 bucket name conflict (bucket already owned by another app — pick a unique bucketKey); 429 rate limited — backoff and retry; 5xx APS upstream outage — retry with jitter. Side effects: NON-IDEMPOTENT. Creates the scanbim-models bucket if absent, uploads a new OSS object with a timestamped key (each call creates a distinct object even for the same input), submits a Model Derivative job (x-ads-force=true overwrites prior derivatives for the same URN), and inserts a row into D1 usage_log + models table.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file_urlYesPublicly fetchable HTTPS URL to the 3D model file. Must be directly downloadable (no login wall, no JS redirect); the worker does a plain fetch() and streams the bytes into APS OSS. Max 100MB for direct upload. Presigned S3/GCS URLs work well.
file_nameYesFilename including the extension. The extension is used to determine the tier (free/pro/enterprise) and is preserved in the OSS object key (prefixed with a Unix-ms timestamp). Use only ASCII + dash/underscore/dot; no path separators.
project_nameNoOptional free-text label stored alongside the model row in D1 for grouping models by project. Does not affect APS storage or URN. Defaults to 'default' when omitted.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed6 schema fields changed
    • changedInput schema / properties / file_name / description
      Previous value: -"Filename with extension (e.g. building.rvt)"New value: +"Filename including the extension. The extension is used to determine the tier (free/pro/enterprise) and is preserved in the OSS object key (prefixed with a Unix-ms timestamp). Use only ASCII + dash/underscore/dot; no path separators."
    • addedInput schema / properties / file_name / examples
      Added value: +[
+  "office-tower-L1-L12.rvt"
+]
    • changedInput schema / properties / file_url / description
      Previous value: -"Public URL to the 3D model file"New value: +"Publicly fetchable HTTPS URL to the 3D model file. Must be directly downloadable (no login wall, no JS redirect); the worker does a plain fetch() and streams the bytes into APS OSS. Max 100MB for direct upload. Presigned S3/GCS URLs work well."
    • addedInput schema / properties / file_url / examples
      Added value: +[
+  "https://storage.googleapis.com/scanbim-public/sample/rac_basic_sample_project.rvt"
+]
    • changedInput schema / properties / project_name / description
      Previous value: -"Project name for organization (optional)"New value: +"Optional free-text label stored alongside the model row in D1 for grouping models by project. Does not affect APS storage or URN. Defaults to 'default' when omitted."
    • addedInput schema / properties / project_name / examples
      Added value: +[
+  "1200 Main St - Tower A"
+]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

No annotations exist, so the description must disclose all behavioral traits. It does so thoroughly: non-idempotency, side effects (bucket creation, timestamped object key, D1 inserts), prerequisites (public URL), rate limits, error classes, and scope requirements. This is exceptional transparency for a mutation tool.

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?

The description is long, but every section serves a purpose: action, format list, usage guidance, exclusions, scopes, rate limits, errors, and side effects. The structure uses clear label prefixes and bullet-like separations, making it scannable despite the length. Minor redundancy exists (e.g., format list is long and somewhat repeated in schema examples), but overall well-organized.

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 complex tool with no annotations and no output schema, the description is extremely thorough. It covers all aspects an agent needs: verb/resource, return values (URN/viewer/QR), prerequisites (public URL, 100MB limit), error handling, rate limiting, side effects, and sibling differentiation. The only minor gap is the lack of explicit response structure beyond the return line, but the description still conveys the necessary execution context.

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 already describes all three parameters with 100% coverage. The description adds value by reinforcing key constraints (max 100MB, direct fetch, extension-based tiering, timestamped key) and clarifying edge cases (presigned URLs work, ASCII-only filenames). This goes beyond simple schema repetition, though the schema already does heavy lifting.

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?

The description opens with a specific verb ('Ingest') and clear resource ('3D model from a public URL into APS OSS') plus the secondary action ('kick off a Model Derivative translation job'). It explicitly states return values (URN, viewer link, QR code), and the format list distinguishes it from sibling tools like get_model_metadata or get_viewer_link.

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?

Dedicated 'When to use' and 'When NOT to use' sections with concrete examples (S3 presigned URL, GitHub raw) and explicit exclusion scenarios (local disk, behind auth). It also names get_model_metadata as the alternative for re-translation, which is actionable guidance.

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

All ScanBIM MCP toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation4/5

Tools are grouped by domain with clear prefixes (acc_, xr_, get_) and each has a distinct purpose. The only potential confusion is between lumion_render and twinmotion_render, but descriptions clarify the aesthetic difference. Overall, tools are clearly differentiated.

Naming Consistency4/5

Most tools follow consistent patterns: acc_* for ACC operations, get_* for metadata retrieval, and xr_launch_*/xr_list_* for XR sessions. Minor deviations like list_models instead of get_models and render tools using software names as prefixes are readable and do not hinder pattern recognition.

Tool Count4/5

At 19 tools, the count is slightly above the ideal range but justified by the server's broad scope covering ACC, model translation, clash detection, rendering, and XR. Some render tools are stubs and could be trimmed, but they are clearly marked as roadmap items.

Completeness3/5

The set covers upload→translate→view→clash-detect→create issues/RFIs workflows well, but lacks update/delete operations for issues and RFIs, and there is no full-detail retrieval for a single issue or RFI. These gaps can cause workflow dead ends for closeout and status changes.

Resources