Simplio3D MCP Server
The Model Context Protocol (MCP) is an open standard that lets AI assistants call external tools through a single, consistent interface. The Simplio3D MCP server exposes your 3D product configurators — projects, option blocks, conditional logic, pricing, materials, 3D model structure, and quote requests — as tools an AI agent can read and, under a controlled-write model, author.
What your agent can do
Instead of describing your configurator to an AI, point the AI at it. With the Simplio3D tools connected, an assistant can inspect a real project, cross-check option blocks against the actual 3D model file, evaluate conditional logic, compute a configuration price, and audit a configurator for broken references — all from your own account data.
Read real projects
Models, option blocks, pricing, forms
Validate configurations
Find broken 3D targets and dead rules
Answer pricing questions
Server-side CPQ calculation
Controlled writes
High-risk changes need your confirmation; every change is undoable
Availability
Simplio3D rolled MCP out in phases, and the transport is now live: the tool layer powers the built-in AI assistant, and external MCP clients connect directly to the remote endpoint with OAuth 2.1 or a scoped connection token. This table remains the authoritative status.
| Capability | Status | Detail |
|---|---|---|
| Tool layer (domain tools) | Available | All 115 tools (51 read + 61 write + 3 workflow operations) are implemented, permission-gated, and running in production. |
| Built-in AI assistant | Available | The in-app assistant calls these tools server-side to answer questions about your real projects. |
| Authenticated REST access | Available | GET /ai/tools and POST /ai/tools/execute expose the same registry to your own automations today. |
| Remote MCP server endpoint | Available | Live at https://app.simplio3d.ai/mcp — stateless Streamable HTTP with OAuth 2.1 or a scoped bearer token from Dashboard → Integrations → AI Connections. |
| Product documentation over MCP | Available | search_documentation and get_documentation_section serve the official published docs (tutorials, REST API, SDK, MCP, changelog) — the only tools that read no workspace data, so the docs:read scope is safe to grant on its own. Agents should cite the returned url rather than answering product questions from recollection. The same content is also reachable through the MCP resources primitive — simplio3d://docs for a search-backed index, and the simplio3d://docs/{page}/{slug} template for one full section — both gated on docs:read. |
| Local stdio bridge package | Planned | A published npx-runnable bridge for MCP clients that prefer a local stdio server. |
| Write tools (create / update) | Available | Phase 2 is live: 61 controlled write tools. High-risk changes (pricing, SKUs, deletions, bulk edits) only ever produce a PROPOSED plan the workspace user must confirm in the app; every applied change is snapshotted (undoable), validated and audited. |
| Store connections (Shopify / WooCommerce) | Available | Agents can read connection status, list store products, and PROPOSE a product link or a checkout-mode change (both high-risk, so the owner applies them in the app, and both need an owner/admin seat). Reading store credentials, connecting or disconnecting a store, and changing a store URL are structurally impossible over this surface — that stays a dashboard wizard. |
| Agent workflows (assistant & REST) | Available | Phase 4 is live on ONE shared engine for the in-app assistant, the authenticated /ai/workflows REST family, and MCP observation: bounded multi-step workflows (project audit, safe repair, material options, catalogue pricing/SKUs, conditional rules, publish-readiness) that orchestrate these same tools, pause for user answers and approvals, checkpoint after every step, and never publish. |
| Workflow entry tools over MCP | Available | Live: 3 workflow operation tools (start_workflow, respond_to_workflow, control_workflow) behind the workflows:write scope. Workflows persist server-side and survive disconnects; questions are relayed to the human user and answers validated against the question's options (the elicitation fallback — the stateless transport declares no elicitation capability); approvals remain in-app only, linked via approvalUrl. |
The MCP endpoint is live
Connect at https://app.simplio3d.ai/mcp — via OAuth 2.1 (add it as a custom connector in Claude) or with a scoped token created in Dashboard → Integrations → AI Connections. See . The authenticated REST tool endpoint is unchanged and still supported — it exposes the identical tool registry with the identical permissions.
How it fits together
Every AI surface shares one tool layer. The built-in assistant, your own automations, and external MCP clients all execute the same registry behind the same authentication, permission, and audit path — so a capability behaves identically wherever it is called from.
Claude · Cursor · VS Code · your automation · Simplio3D AI assistant
│
▼
Simplio3D Tool Layer (one registry)
authentication · workspace scoping · role permissions
schema validation · result sanitization · audit logging
│
▼
Projects · Option blocks · Conditional logic
Pricing · Materials · 3D models · QuotesWhat is not exposed
Agents never receive database access, service credentials, API keys, SMTP or webhook secrets, e-commerce store tokens, or share passwords. Tools return curated summaries, not raw records — see .
