Inspect a 3D model

Inspect a model's counts, bounds, units, materials and texture references. Compare stored topology with an analysis copy that merges exactly coincident vertices. Get a short summary and a detailed JSON report, without changing or segmenting the model.

Formats

.glb .gltf .obj .ply .stl .off .blend

Outputs

inspection.json and summary.txt

Dimensions

World-space bounds; units unknown when unspecified

Topology

Components, boundary edges, non-manifold edges, degenerate faces and watertightness

Blender

Evaluated meshes; pack resources into the file

Send the file as the request body with the options in the query string, or refer to it in a JSON body (upload_id or url) with an options object. The response is the new job; poll it until its status is final, then download the files in result.files.

curl "https://api.mcpbytes.com/v1/tools/inspect_3d_model/jobs?filename=cube.glb" \
  -H "Authorization: Bearer $MCPBYTES_API_KEY" \
  --data-binary @cube.glb

{
  "tool": "inspect_3d_model",
  "status": "queued",
  "options": {},
  "result": null
}

# JOB_ID is the id from the create response
curl "https://api.mcpbytes.com/v1/jobs/$JOB_ID" \
  -H "Authorization: Bearer $MCPBYTES_API_KEY"

# Once status is succeeded, read the report
curl "https://api.mcpbytes.com/v1/jobs/$JOB_ID/files/inspection.json" \
  -H "Authorization: Bearer $MCPBYTES_API_KEY"

{
  "tool": "inspect_3d_model",
  "status": "succeeded",
  "result": {
    "schema_version": 1,
    "object_count": 1,
    "mesh_instance_count": 1,
    "vertex_count": 8,
    "face_count": 12,
    "details_truncated": false,
    "notes": []
  }
}

A job can be canceled while it is queued: POST /v1/jobs/{id}/cancel.

More on statuses, downloads and retention in Jobs & files.

One file per job, in one of these ways. The formats it accepts are listed in the overview.

# 1. Create an upload URL (valid for one hour)
curl https://api.mcpbytes.com/v1/uploads \
  -H "Authorization: Bearer $MCPBYTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"filename": "cube.glb"}'

# 2. PUT the file to the "url" from the response
curl -X PUT --data-binary @cube.glb "$UPLOAD_URL"

# 3. Start the job with the "upload_id"
curl https://api.mcpbytes.com/v1/tools/inspect_3d_model/jobs \
  -H "Authorization: Bearer $MCPBYTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"upload_id\": \"$UPLOAD_ID\"
  }"

To retry safely, send an Idempotency-Key header (or idempotency_key in a JSON body): a repeated key returns the original job instead of starting a new one.

This tool has no options: the input is all it needs.

A succeeded job lists its files in result.files, each with a download url.

Read either file with read_job_file or download it from result.files. Stored and merged topology are reported separately, without cross-instance welding. Watertightness is not a printability or self-intersection test. Reports over 10 MiB omit detailed arrays and set details_truncated.

Result summary

Next to files, the job's result has a summary you can check without downloading anything:

• Over MCP, summary.txt comes back with the result. Read inspection.json with read_job_file, or GET /v1/jobs/{id}/files/inspection.json.
• Topology is reported twice: as stored, and with exactly coincident vertices merged on an analysis copy. Compare them to tell vertex seams from real open boundaries.
• Watertight is a topology check. It does not detect self-intersections or certify printability.
• External resources are never fetched: pack textures into the file. Missing optional textures produce warnings; missing geometry fails the job.
• Inspect, then split with the same upload_id while the upload lasts. Each is its own job.

Your agent calls inspect_3d_model. Connect it to https://api.mcpbytes.com/mcp/3d for this tool and the rest of its family (Create a 3D model, Create a 3D model from an image, Optimize a 3D model, Simplify a 3D model, Split a 3D model into parts), or to https://api.mcpbytes.com/mcp for every tool.

claude mcp add --transport http mcpbytes \
  https://api.mcpbytes.com/mcp/3d

codex mcp add mcpbytes --url https://api.mcpbytes.com/mcp/3d \
  --bearer-token-env-var MCPBYTES_API_KEY

{
  "mcpServers": {
    "mcpbytes": {
      "url": "https://api.mcpbytes.com/mcp/3d",
      "headers": {
        "Authorization": "Bearer ${env:MCPBYTES_API_KEY}"
      }
    }
  }
}

Arguments

The tool's options are flat arguments. Besides them:

What the agent sees

Setup for every client, and how agents upload files and read results: Connect over MCP.

The MCPBytes skill teaches agents this tool, in references/inspect_3d_model.md. Agents without MCP run it through the REST API with the skill's script, which reads your key from MCPBYTES_API_KEY:

python scripts/mcpbytes.py run inspect_3d_model model.glb --out inspection/
python scripts/mcpbytes.py read j_... inspection.json

From 10 credits. The price follows the input's size and is charged once the input has been measured; starting a job needs at least the smallest price. A job that fails costs nothing: its charge is refunded.

One credit balance pays for every tool, and a new account starts with free credits. See Credits & prices or buy credits.

GET /v1/me returns your limits and current usage; Limits & errors explains what happens when one is reached.

A failed job comes back with error.code, error.message and often error.hint. Codes are stable. Inputs that fail with a validation error will fail again unchanged.

Requests can also fail before a job starts, with an HTTP status: see HTTP errors.

• Split a 3D model into partsSplit the model into parts once the report looks right.split_3d_model
• Simplify a 3D modelReduce a model whose face count is too high for the next step.simplify_3d_model