Skip to main content
Glama
aydinfer
by aydinfer

exportSceneCode

Generate code for 3D scenes from Spline in vanilla JavaScript, React, or Next.js formats to integrate interactive designs into web applications.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sceneIdYesScene ID
formatNoExport formatvanilla

Implementation Reference

  • Registration of the exportSceneCode MCP tool with input schema and handler function that delegates to runtimeManager.generateRuntimeCode
    server.tool(
      'exportSceneCode',
      {
        sceneId: z.string().min(1).describe('Scene ID'),
        format: z.enum(['vanilla', 'react', 'next']).default('vanilla')
          .describe('Export format'),
      },
      async ({ sceneId, format }) => {
        try {
          const code = runtimeManager.generateRuntimeCode(sceneId, format);
          
          return {
            content: [
              { 
                type: 'text', 
                text: code 
              }
            ]
          };
        } catch (error) {
          return {
            content: [
              { 
                type: 'text', 
                text: `Error generating code: ${error.message}` 
              }
            ],
            isError: true
          };
        }
      }
    );
  • Zod input schema defining sceneId (required string) and format (optional enum: 'vanilla', 'react', 'next', defaults to 'vanilla')
    {
      sceneId: z.string().min(1).describe('Scene ID'),
      format: z.enum(['vanilla', 'react', 'next']).default('vanilla')
        .describe('Export format'),
    },
  • MCP tool handler function that invokes runtimeManager.generateRuntimeCode and returns the generated code as text content or error
    async ({ sceneId, format }) => {
      try {
        const code = runtimeManager.generateRuntimeCode(sceneId, format);
        
        return {
          content: [
            { 
              type: 'text', 
              text: code 
            }
          ]
        };
      } catch (error) {
        return {
          content: [
            { 
              type: 'text', 
              text: `Error generating code: ${error.message}` 
            }
          ],
          isError: true
        };
      }
    }
  • Core helper function that generates the runtime integration code for the Spline scene in specified format (vanilla JS, React, or Next.js), constructing the scene URL and providing example interaction code.
      generateRuntimeCode(sceneId, format = 'vanilla') {
        const sceneUrl = `https://prod.spline.design/${sceneId}/scene.splinecode`;
        
        if (format === 'vanilla') {
          return `
    import { Application } from '@splinetool/runtime';
    
    // Create a new Application instance
    const canvas = document.getElementById('canvas3d');
    const spline = new Application(canvas);
    
    // Load the scene
    spline.load('${sceneUrl}').then(() => {
      console.log('Scene loaded successfully');
      
      // Access the Spline Application API
      // Get an object by name
      const myObject = spline.findObjectByName('Cube');
      
      // Or get an object by ID
      // const myObject = spline.findObjectById('...');
      
      // Interact with the object
      if (myObject) {
        // Modify properties
        myObject.position.y += 1;
        myObject.rotation.y = Math.PI / 4;
        
        // Listen for events
        spline.addEventListener('mouseDown', (e) => {
          if (e.target === myObject) {
            console.log('Object clicked!');
          }
        });
        
        // Emit events
        myObject.emitEvent('mouseDown');
      }
    });
    `;
        } else if (format === 'react') {
          return `
    import React, { useRef } from 'react';
    import Spline from '@splinetool/react-spline';
    
    export default function Scene() {
      const objectRef = useRef();
      
      function onLoad(splineApp) {
        console.log('Scene loaded successfully');
        
        // Save references to objects
        objectRef.current = splineApp.findObjectByName('Cube');
      }
      
      function handleClick() {
        if (objectRef.current) {
          // Modify object properties
          objectRef.current.position.y += 1;
        }
      }
    
      return (
        <div style={{ width: '100%', height: '100%' }}>
          <button onClick={handleClick}>Move Object Up</button>
          <Spline 
            scene="${sceneUrl}" 
            onLoad={onLoad}
            onMouseDown={(e) => {
              console.log('Mouse down on:', e.target.name);
            }}
          />
        </div>
      );
    }
    `;
        } else if (format === 'next') {
          return `
    import React, { useRef } from 'react';
    import dynamic from 'next/dynamic';
    
    // Import Spline component with no SSR
    const Spline = dynamic(() => import('@splinetool/react-spline/next'), {
      ssr: false,
      loading: () => <div>Loading 3D scene...</div>
    });
    
    export default function Scene() {
      const objectRef = useRef();
      
      function onLoad(splineApp) {
        console.log('Scene loaded successfully');
        
        // Save references to objects
        objectRef.current = splineApp.findObjectByName('Cube');
      }
      
      function handleClick() {
        if (objectRef.current) {
          // Modify object properties
          objectRef.current.position.y += 1;
        }
      }
    
      return (
        <div style={{ width: '100%', height: '100%' }}>
          <button onClick={handleClick}>Move Object Up</button>
          <Spline 
            scene="${sceneUrl}" 
            onLoad={onLoad}
            onMouseDown={(e) => {
              console.log('Mouse down on:', e.target.name);
            }}
          />
        </div>
      );
    }
    `;
        } else {
          throw new Error(`Unsupported format: ${format}`);
        }
      }
Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aydinfer/spline-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server