MCP · Hosted & OAuth

Agentic CAD with MCP

The client provides the AI. confBuild provides prompts, projects, sheet changes, validation, and visual feedback.

The confBuild MCP server connects an AI-capable client such as Codex or Claude to confBuild. You can request a new house, machine, product, or 3D-print part in natural language—or provide an existing project link or ID and ask the agent to continue editing it.

The key boundary: model intelligence stays in the MCP client. The server does not call OpenAI, Anthropic, Gemini, or the confBuild prompt editor's AI endpoints. The MCP server therefore creates no second model API bill. Normal usage or billing for your chosen client still applies.

How the components work together

1. User

Describes the goal and optionally supplies an existing confBuild link or project ID.

2. Codex or Claude

Reads the master prompts, plans the geometry, generates Sheet data, and analyzes screenshots.

3. MCP server

Provides deterministic tools for project access, patches, validation, persistence, and browser rendering.

4. confBuild

Stores the private project, evaluates the spreadsheets, and renders the actual 3D result in the editor.

The closed agent loop is:

  1. The client starts a design session and loads the appropriate prompt bundle.
  2. It creates a private project or opens/clones an existing one.
  3. It reads and changes the confBuild Sheets in a local edit session.
  4. The server validates and saves changes with revision protection.
  5. A browser renders multiple views; screenshots and diagnostics return to the client.
  6. The client evaluates the result itself and repeats the loop until the model is complete.

What you can do

✦

Generate from language

Start with a sentence such as “Generate a conveyor machine with adjustable length and a safety cover.”

↗

Continue from a link

Provide an ID or a supported /e/, /editor/, /p/, or /lib/ URL.

▦

Change Sheets precisely

The client can update a complete workbook, individual sheets, rows, or cells.

◎

Iterate visually

Four browser views and Three.js diagnostics support a recognize → inspect → correct loop.

Three ways to start

Starting point Behavior
Description only The client creates a new private project.
Your private link or ID The project is edited directly with revision protection.
Public or read-only link The server first creates a private editable copy.

For a bare ID, the server checks the authenticated user’s private workspace first and the public collection second. It never guesses another user’s private owner path.

Example requests

Generate a configurable two-story family house with a gable roof,
garage, and large south-facing windows.

Continue editing https://app.confbuild.com/e/PROJECT_ID.
Add a safety enclosure, a maintenance door, and height-adjustable feet.
Inspect the result in every screenshot view.

Create an FDM-printable sensor enclosure for an 80 × 50 mm PCB,
with 2.4 mm walls, M3 screw bosses, and ventilation slots.

The more clearly you specify dimensions, units, motion ranges, materials, and acceptance criteria, the more directly the client can model. The agent may make reasonable assumptions for ambiguous details; safety- or standards-critical assumptions should be confirmed explicitly.

Requirements

  • Codex, Claude, or another client with remote MCP and OAuth support
  • A normal confBuild user account for private projects
  • A browser in which the target project can remain open for screenshots

The customer-ready Remote MCP is live at https://app.confbuild.com/mcp. It uses Streamable HTTP and OAuth with PKCE. Customers install neither the repository nor Node/npm/NuGet and need no confBuild API key. The local STDIO mode remains available separately for development and repository automation.

Install as a one-click package

The confBuild plugin bundles the Remote MCP, OAuth connection, the confbuild-mcp-agent skill, and host metadata into one installation. Once it is publicly available, customers only need to find confBuild in their client’s plugin directory, install the package, approve OAuth access once, and then use the skill directly in Codex/ChatGPT or Claude Code. No repository, Node/npm, API token, or manual skill copying is required.

The package is publicly available through the self-hosted confBuild beta marketplace; the OpenAI universal directory and Anthropic community reviews remain pending. Entering the Remote MCP URL directly remains the manual compatibility path: it provides the tools and dynamic confbuild-design prompt, but it does not install a client skill. Use the plugin installation page or see Set up MCP for the full procedure.

Production verified: the live test covers sign-in → OAuth/PKCE → project creation → Sheet edit and commit → project readback → browser render → PNG return to the MCP client.

Continue reading

M1

Setup

Set up the one-click package, OAuth, or the manual transition path.

 M2

Project workflow

Work with new and existing projects through the complete agent loop.

 M3

Prompts & AI boundary

Understand which master prompts the client receives and who performs the AI work.

 M4

Screenshots

Browser modes, views, diagnostics, and visual acceptance criteria.

 M5

Tool reference

All MCP tools, patch operations, and state boundaries.

 M6

Security & help

Permissions, revision conflicts, limitations, and common fixes.

What the MCP server deliberately does not decide

The server is not a second AI model or a CAD approval authority. It does not independently turn language into a complete model, interpret screenshots, or guarantee structural safety, manufacturability, collision freedom, or standards compliance. Those evaluations belong to the client and—for professionally critical results—to the responsible human.

Back to Documentation