- Home
- Skills
- Agents & Orchestration
- Forma 3D Modeling
Forma 3D Modeling
Create, verify, measure, and export parametric 3D models with the real Forma geometry engine.
$5
Works with the AI Agents you already use
Forma 3D Modeling
Example session with this skill installed
Build me a parametric stylized tree as tree.forma, with an adjustable trunk height and canopy layer count. Validate every part with the geometry kernel and report the overall dimensions and topology before saving it.
- Read your context and instructions
- Compiled the forma 3d modeling
Model created and verified
I created tree.forma inside the active workspace root. Before writing the file, Forma compiled the document and solved both parts with the Manifold geometry kernel. The parameters remain editable, so you can change the trunk height or canopy layer count and re-run the same validation.
| Part | Colour | Size (X × Y × Z) | Volume | Triangles | Genus |
|---|---|---|---|---|---|
trunk | #6b4423 | 8 × 8 × 30 | 1004.682 | 108 | 0 |
canopy | #2f7d32 | 28 × 28 × 30 | 5193.4555 | 358 | 0 |
Overall bounding box: 28 × 28 × 51
Bounds: minimum [-14, -14, 0], maximum [14, 14, 51]
Total triangles: 466
Both parts produced non-empty, closed solids with genus 0. The verified source is saved as tree.forma; no STL was exported because the request only asked for the Forma document. If you want a printable mesh, ask me to export tree.forma as tree.stl and I will run the export through the same geometry engine.
Connects securely to your tools. The creator never sees your data.
About this skill
Verified 3D modeling for AI agents
Forma makes 3D geometry a readable source file that can be edited, reviewed in Git, parameterized, tested, and exported. This skill teaches an agent when and how to use forma-dsl-mcp, the MCP server backed by Forma's real geometry kernel.
What it does
- Creates and modifies
.formamodels using the language's own guide, catalogue, examples, and reference. - Validates every document before it is written.
- Reports each part's bounding box, volume, triangle count, and genus.
- Refuses invalid documents and identifies empty geometry by part name.
- Exports verified models as binary STL files when requested.
Why it is different
This is not a prompt that asks an LLM to guess CAD syntax. The MCP server carries the Forma language with it and runs every document through the Manifold geometry kernel. A model is only reported as successful after it has actually solved and been measured.
Outputs remain normal .forma and .stl files inside the workspace roots provided by the MCP client, so they can be edited, committed, reviewed, and built outside the chat.
Good fits
Parametric parts, 3D-printable models, product configurators, reusable geometry components, automated model variations, CI-driven STL generation, and agent-assisted solid modeling.
Requires Node.js 22.13+. Limited to code-defined solid modeling; not for photorealistic rendering or interactive assemblies. Must stay within MCP workspace roots.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires
Permissions
File Scopes
Reads and writes only inside workspace roots exposed by the MCP client. Network access is needed only for `npx` to obtain the npm package; the server itself makes no network requests while modeling.