
Mantis Mcp
io.github.kahlilashantiPublished by GitHub account kahlilashantiv1.1.0Updated Oct 24, 2026
Build proven high converting product showrooms and websites from your existing ecommerce catalog
Overview
Mantis MCP lets an AI assistant generate integration code for Mantis immersive commerce showrooms and, when configured, create and publish showrooms from a shop
- What you can do
- Generate SDK install steps and framework-specific integration code for React, Vue, Next.js, Shopify or vanilla JavaScript, plus event handler code for Mantis SDK events. Diagnose console errors and check browser compatibility for WebGL, postMessage and fullscreen features. Validate an SDK setup, import product catalogs from Shopify, CSV or manual input, and create or publish immersive showrooms. Simulate postMessage debugging, SDK event tests, user flows, performance metrics and event-flow analysis with mock data.
- When to use it
- Useful when adding the Mantis immersive showroom SDK to a storefront and wanting generated integration code, error diagnosis and compatibility checks. Also relevant for teams already on Mantis who want an assistant to help create, validate or publish showrooms from an existing catalog.
- Requirements
- Runs locally via npx or a global npm install, so Node.js is needed. Optional MANTIS_API_URL and MANTIS_AUTH_TOKEN connect it to a real Mantis instance; Mantis users receive these during account setup. Without them, tools use simulated data.
Installation
In SourceWeft
- Open Mantis Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Mantis MCP Server
AI assistant tools for building high-converting immersive commerce showrooms from your existing e-commerce catalog. Built on Mantis's production immersive-commerce platform, used by Fortune 500 brands including New Balance, with deployments spanning the Paris 2024 Olympics, MLB, NHL, and the Premier League.
Part of Mantis's vision for agent-invoked immersive commerce infrastructure. Learn more at mantisxr.com.
Quick Start
Or install globally:
Then configure in Claude Desktop, Cursor, or any MCP-compatible client (see Configuration below).
Status
The Mantis showroom platform this MCP connects to is live in production, used by Fortune 500 brands including New Balance, with deployments including the Paris 2024 Olympics, Chicago Cubs (MLB), St. Louis Blues (NHL), and Burnley FC and other Premier League clubs. This MCP server is how that platform gets exposed to AI agents, and it's actively in development. Some tools are fully wired to the real platform API today; others are simulated while backend endpoints are being built out. See the tool status below for exactly what's real versus in progress.
Setup
Environment Variables (Optional)
Configure these to connect to the real Mantis API:
Mantis users receive their API URL and auth token during account setup. Without these, tools work with simulated data for code generation and planning.
Configuration
Claude Desktop:
- Open Settings → Developer → Edit Config
- Add:
Cursor:
- Settings → MCP Servers → Add new server
- Configure with
npx mantis-mcp
Other MCP clients: Use npx mantis-mcp or node /path/to/dist/index.js
Tools
✅ Fully Working (no API required)
installMantisSDK Generates installation commands and .npmrc setup for integrating Mantis SDK into React, Vue, Next.js, Shopify, or vanilla JavaScript projects.
createMantisIntegration Generates complete, framework-specific integration code with event handlers, cart integration, and analytics tracking.
generateEventHandler Creates event handler code for Mantis SDK events (cart-opened, model-click, variant-changed, etc.).
analyzeConsoleErrors Pattern-matches common errors (SDK not loaded, postMessage blocked, WebGL issues) and provides fixes with code examples.
checkBrowserCompatibility Checks browser compatibility for WebGL, postMessage, fullscreen, and other immersive features with polyfill recommendations.
🟡 Partially Working (uses real API when configured)
validateSetup
Validates Mantis SDK installation. Calls real showrooms.getShowroom API if MANTIS_API_URL is configured, otherwise returns sample validation checks.
importCatalog Imports product catalogs from Shopify (real API), CSV, or manual input. Data parsed successfully; backend storage endpoints pending.
createStore
Creates an immersive showroom. Attempts real showrooms.createShowroom API call if configured, falls back to mock response with guidance.
publishStore
Publishes showroom live. Attempts real showrooms.updateShowroom API if configured, otherwise simulates status change to active.
🔴 Mocked (simulated data, backend endpoints pending)
debugPostMessage Simulates postMessage debugging scenarios with realistic message timelines, origin checks, and error patterns.
testMantisEvent Simulates SDK event testing (model-loaded, add-to-cart, etc.) with validation and performance timing.
simulateUserFlow Simulates multi-step user interaction flows (load → click → add-to-cart) with realistic delays and error scenarios.
getPerformanceMetrics Generates simulated performance data (FPS, load times, memory, GPU) based on requested metrics.
analyzeEventFlow Simulates event flow analysis with conversion funnels, dropoff points, and user behavior patterns.
What This MCP Does Not Do
Immersive Asset Generation: Mantis does not provide automated conversion of product photos into immersive-ready assets. Merchants must provide immersive-ready assets (.glb/.gltf files) when creating products. This is an intentional scope decision: automated asset generation is a commoditizing service layer that multiple companies have attempted without building sustainable businesses. Mantis's value is the immersive showroom platform, merchandising intelligence, and agent-invokable commerce infrastructure—not asset generation.
Development
License
MIT
Links
Source: README.md at commit aeb2bf2
Tools
0Version history
1- v1.1.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts