Skip to main content
Glama

Revit MCP

by io.scanbimlabs

revit_upload

When to use: Ingest a Revit (.rvt / .rfa / .rte / .rft) file into Autodesk Platform Services by downloading it from a publicly reachable URL, uploading it to an OSS bucket, and starting an SVF2 translation so downstream revit_* tools can read elements, parameters, sheets, and views. When NOT to use: Do not call if you already have a translated URN (use the existing model_id instead), if the file is not a Revit source file, or if the URL requires authentication the worker cannot satisfy. APS scopes: data:read data:write data:create bucket:read bucket:create viewables:read (OSS bucket create + object PUT + Model Derivative job). 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 — refresh credentials and retry. 403 scope insufficient — request data:write + bucket:create. 404 bucket/object not found — confirm bucket was created. 409 bucket exists — safe to ignore, reuse it. 429 rate limited — back off with exponential delay. 5xx APS upstream — retry with jitter up to 3x, then surface. Side effects: Creates a new transient OSS bucket named scanbim-revit-, uploads the object, and starts a Model Derivative translation job. NOT idempotent — each call creates a fresh bucket and new URN.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file_urlYesPublic HTTPS URL the worker can fetch the Revit file from. Must return 200 with the raw .rvt bytes (no auth gate, no HTML redirect). Max 100MB for direct upload.
file_nameYesOriginal file name including the Revit extension (.rvt, .rfa, .rte, .rft). Used as the OSS object key; non-alphanumeric characters are sanitized to underscores.
project_nameNoOptional human-readable project label echoed back in the response for bookkeeping. No effect on APS processing.

Schema Changelog

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

  1. Changed8 schema fields changed
    • changedInput schema / properties / file_name / description
      Previous value: -"Name for the file (e.g. 'MyBuilding.rvt')"New value: +"Original file name including the Revit extension (.rvt, .rfa, .rte, .rft). Used as the OSS object key; non-alphanumeric characters are sanitized to underscores."
    • addedInput schema / properties / file_name / examples
      Added value: +[
+  "MyBuilding.rvt"
+]
    • addedInput schema / properties / file_name / pattern
      Added value: +"^[A-Za-z0-9._-]+\\.(rvt|rfa|rte|rft)$"
    • changedInput schema / properties / file_url / description
      Previous value: -"Public URL to download the .rvt file from"New value: +"Public HTTPS URL the worker can fetch the Revit file from. Must return 200 with the raw .rvt bytes (no auth gate, no HTML redirect). Max 100MB for direct upload."
    • addedInput schema / properties / file_url / examples
      Added value: +[
+  "https://example.com/models/MyBuilding.rvt"
+]
    • addedInput schema / properties / file_url / format
      Added value: +"uri"
    • changedInput schema / properties / project_name / description
      Previous value: -"Optional project label"New value: +"Optional human-readable project label echoed back in the response for bookkeeping. No effect on APS processing."
    • addedInput schema / properties / project_name / examples
      Added value: +[
+  "Acme HQ Tower - Phase 2"
+]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description fully carries the transparency burden. It discloses side effects (creates a transient bucket, uploads, starts translation), non-idempotency ('NOT idempotent — each call creates a fresh bucket and new URN'), rate limits, and detailed error handling. This is exemplary behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear section headings (When to use, When NOT to use, APS scopes, Rate limits, Errors, Side effects). Every sentence contributes actionable information; it is long but not verbose. The front-loaded usage guidelines make it easy to navigate.

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?

Despite no output schema, the description explains the full processing pipeline, side effects, rate limits, error scenarios, and downstream consequences. It even implies the output (a new URN) through side-effect disclosure. For a tool of this complexity, the description is thorough and self-sufficient.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already fully documents all parameters. The description adds only a general mention of the 100MB size limit (already present in the file_url schema description) and does not provide new parameter semantics beyond the schema. Baseline 3 is appropriate.

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 clearly states the tool's function: 'Ingest a Revit (.rvt / .rfa / .rte / .rft) file... downloading it from a publicly reachable URL, uploading it to an OSS bucket, and starting an SVF2 translation'. This specific verb+resource+process makes it easily distinguishable from sibling tools like revit_get_elements, which are read-focused.

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?

Explicit 'When to use' and 'When NOT to use' sections are provided, with concrete exclusions (e.g., 'Do not call if you already have a translated URN') and a direct alternative ('use the existing model_id instead'). Also mentions the downstream benefit for revit_* tools, giving clear contextual guidance.

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

All Revit 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

A4.5/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: upload ingests, get_elements/get_parameters/get_sheets/get_views retrieve different types of data, run_schedule queries tabular views, clash_detect performs spatial analysis, and export_ifc converts formats. No two tools overlap in function; even get_sheets and get_views are explicitly differentiated in their descriptions.

Naming Consistency5/5

All tools follow a consistent revit_<verb> pattern in snake_case, with get_* for read operations and action verbs for other operations. The naming is predictable and uniform across the entire set.

Tool Count5/5

Eight tools is well within the ideal 3-15 range and appropriately matches the server's scope of Revit model ingestion, exploration, analysis, and export. Each tool earns its place without redundancy or bloat.

Completeness3/5

The tool set covers the core lifecycle (upload, read elements/parameters/sheets/views, run schedules, clash detect, export IFC), but there is no tool to check translation status or poll the manifest, which is referenced in descriptions but not provided. This is a notable gap that can cause agents to call read tools before translation completes, leading to failures.

Resources