cad-mcp

by Arookie127

Overview Schema Source Related Servers Discussions Admin

Python

Local

export_mesh

Export CAD models as STL or OBJ for 3D printing, slicing, and DCC, blocking broken solids; use force=True to override.

Instructions

Export the model as files for downstream tools: STL (printing / slicing), OBJ+MTL (DCC).

Defaults to both STL and OBJ. There is a hard gate before anything is written: structural damage -- non-manifold edges, non-positive volume, NaN vertices, a fragmented shell -- is refused, because such a mesh punches holes in a slicer or errors out. Watertightness only warns (some shapes are meant to be open). Pass force=True to override.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "export_mesh"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes
`force`	No
`formats`	No
`stl_binary`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 2, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses a hard pre-write gate (non-manifold edges, non-positive volume, NaN vertices, fragmented shell are refused), distinguishes that watertightness only warns, and documents the force override. It stops short of stating where files are written, whether existing files are overwritten, or what is returned.

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?

Front-loads the core action and format list, then the gate behavior. Every sentence carries information, though the gate explanation is dense and could be trimmed slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter mutation tool with no output schema and no annotations, the description covers validation/override behavior well but omits the required `name` parameter's meaning, the stl_binary toggle, and any return/output location, leaving gaps an agent must guess at.

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 description coverage is 0%, so the description must compensate. It documents formats and force (including the gate override), but leaves the required `name` parameter and `stl_binary` (binary vs ASCII STL) entirely unexplained, so it only partially closes the coverage gap.

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?

States a specific verb (export) and resource (the model) and names the concrete output formats (STL for printing/slicing, OBJ+MTL for DCC), which is exactly the kind of differentiation needed against siblings like check_mesh and look_at_mesh. An agent can tell what this produces without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the selection context (downstream tools), the default of both formats, and the force=True override for the validation gate. It does not explicitly route to siblings such as check_mesh as a pre-flight step, but the when-to-use and override conditions are clear.

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

Deploy Server