Which integrations are available for this server?

Provides blockchain authentication using Ethereum for secure access control based on token holdings.

How do I use Context3D MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Context3D MCP Server generate a 3D model of a medieval sword with PBR textures" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Context3D MCP Server

Official

by Context3D

Overview Schema Related Servers Score Discussions

JavaScript

Remote

Context3D - AI-Powered 3D Model Generation with MCP

🔍 Overview

This repository contains the Context3D MCP Server, a specialized component that integrates the advanced Context3D AI-powered 3D asset generation capabilities with the Model Context Protocol (MCP). While the core Context3D services handle the complex process of generating production-ready 3D models from text prompts or reference images using proprietary diffusion models and extensive datasets, this MCP server provides a standardized interface to access these capabilities via MCP.

The core Context3D services leverage a multi-stage pipeline for 3D asset generation, including input processing, feature extraction, latent space modeling, and asset generation components. This results in high-quality, CG-friendly assets compatible with Unity, Unreal Engine, Maya, and other industry-standard platforms.

This repository's focus is the MCP server, which includes a secure authentication layer that can use blockchain technology to verify users based on their token holdings before allowing access to the underlying Context3D generation services.

Key Features of the Context3D Platform:

Text-to-3D: Generate detailed 3D models from text descriptions
Image-to-3D: Convert reference images into 3D models with matching textures
Hyper-realistic PBR textures: Auto-generated diffuse, normal, roughness, and metallic maps
Production-ready output: Optimized topology and UV mapping for immediate use
Multi-platform compatibility: Export to common formats (.fbx, .obj, .gltf, .usd)
Facial specialization: Advanced capabilities for human facial asset generation

Key Features of this MCP Server:

MCP Integration: Full compatibility with the Model Context Protocol for accessing Context3D services.
Blockchain Authentication: Secure access control based on token holdings for using the Context3D services via MCP.
File Management Tools: Built-in MCP tools for managing generated assets.
Customization Options: MCP interface for controlling core Context3D model generation parameters.

Related MCP server: meshy-youtube-mcp

🏗️ Technical Architecture

This repository focuses on the MCP Server component, which interacts with the core Context3D Cloud Service.

Core Context3D Cloud Service Pipeline (Detailed in plant.md)

The core Context3D Cloud Service utilizes a multi-stage pipeline:

graph TD
    A[Context3D Architecture] --> B[Input Processing]
    B --> C[Feature Extraction]
    C --> D[Latent Space Modeling]
    D --> E[Asset Generation]

    subgraph "Input Processing"
        B1[Text Input Processing]
        B2[Image Input Processing]
        B3[Parameter Config]
        B1 <--> B2
        B2 <--> B3
    end

    subgraph "Feature Extraction"
        C1[Semantic Encoder]
        C2[Visual Encoder]
        C3[Style Encoder]
        C1 <--> C2
        C2 <--> C3
    end

    subgraph "Latent Space Modeling"
        D1[3D Diffusion Model]
        D2[Multi-view Consistency]
        D3[Geometry Refinement]
        D1 <--> D2
        D2 <--> D3
    end

    subgraph "Asset Generation"
        E1[Mesh Generation]
        E2[Texture Generation]
        E3[UV Mapping]
        E4[Topology Optimization]
        E5[PBR Material Creation]
        E6[Export Pipeline]
        E1 <--> E2
        E2 <--> E3
        E1 <--> E4
        E2 <--> E5
        E3 <--> E6
        E4 <--> E5
        E5 <--> E6
    end

    B --> B1
    B --> B2
    B --> B3
    C --> C1
    C --> C2
    C --> C3
    D --> D1
    D --> D2
    D --> D3
    E --> E1
    E --> E2
    E --> E3
    E --> E4
    E --> E5
    E --> E6

Note: This diagram represents the core Context3D Cloud Service pipeline, not the MCP Server in this repository.

MCP Server Communication Flow

This diagram illustrates the communication flow between an MCP client and the server, including interaction with the core Context3D Cloud Service:

sequenceDiagram
    participant Client as MCP Client
    participant Server as Context3D MCP Server
    participant CloudService as Context3D Cloud Service

    Client->>+Server: Execute generate_3d_model tool
    Server->>Server: Perform Authentication/Verification (if enabled)
    Server->>+CloudService: Forward generation request to Cloud Service API Gateway
    CloudService->>CloudService: Process Generation (Input, Feature, Latent, Asset stages)
    CloudService-->>-Server: Return task UUID and status
    Server-->>-Client: Return confirmation with task UUID

    alt With Blockchain Authentication
        Client->>+Server: Execute generate_rodin_model_with_auth tool
        Server->>Server: Verify Ethereum signature & token balance
        Server->>+CloudService: Forward authenticated request to Cloud Service API Gateway
        CloudService->>CloudService: Process Authenticated Generation
        CloudService-->>-Server: Return authenticated response
        Server-->>-Client: Return confirmation with task UUID
    end

    Client->>+Server: Execute download_rodin_results_with_auth tool
    Server->>Server: Verify Ethereum signature & token balance
    Server->>+CloudService: Request download URLs from Cloud Service API Gateway
    CloudService->>CloudService: Retrieve Download URLs
    CloudService-->>-Server: Return authenticated URLs
    Server-->>-Client: Return download links

Authentication Flow (within MCP Server)

The blockchain authentication process within the MCP Server works as follows:

graph TD
    A[User Signs Message] --> B[Generate Ethereum Signature]
    B --> C[Send Request with x-api-key Header to MCP Server]
    C --> D[MCP Server Verifies Signature]
    D --> E[Recover Ethereum Address]
    E --> F[Check Token Balance on Blockchain]
    F --> G{Sufficient Balance?}
    G -- Yes --> H[Proceed with Request to Cloud Service]
    G -- No --> I[Return Error: Insufficient Tokens]

MCP Integration Guide

Adding the MCP Server to Claude Desktop

Follow these steps to integrate the Context3D MCP server with Claude Desktop:

Install Claude Desktop:
- Download the latest version of Claude Desktop from the official website (https://claude.ai/download)
- Follow the installation prompts for your operating system (Windows, macOS)
- Complete the installation and launch Claude Desktop
- Sign in with your Anthropic account credentials if prompted
Configure Claude Desktop:
- Install Node.js (version 16 or higher) from https://nodejs.org
- Clone the Context3D MCP server repository:
  git clone https://github.com/Context3D/context3d-model-mcp-server cd context3d-model-mcp-server
- Install dependencies using your preferred package manager:
  npm install # or pnpm install # or yarn install
- Build the MCP server:
  pnpm build
- Create or update the Claude configuration file. On Windows, this is typically located at %APPDATA%\Claude\claude_desktop_config.json. On macOS, it's at ~/Library/Application Support/Claude/claude_desktop_config.json.
- Add the following JSON configuration, making sure to replace the path with your actual build directory path:
  { "mcpServers": { "filesystem": { "command": "node", "args": [ "/full/path/to/context3d-model-mcp-server/build/index.js" ], "env": { "SAVE_TO_DESKTOP": "true" } } } }
- Save the configuration file and restart Claude Desktop
- Verify the MCP server is running by checking for the Context3D tools in the tools panel
Using the Server:

https://x.com/Context3D/status/1922998936219873558

Available Tools

7 tools

check_statusA

Checks the status of the 3D model generation process using the subscription_key received from generate_model. This tool returns the status of all jobs related to the model. When all jobs have a 'Done' status, proceed to the download_model step to download the model. If any jobs are not completed (Generating, Waiting), notify the user to wait and check again later. Status can be: 'Done' (completed), 'Generating' (in progress), or 'Waiting' (queued).

ParametersJSON Schema

Name	Required	Description	Default
`subscriptionKey`	Yes	The subscriptionKey of the task to check status for

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries full burden. It discloses possible statuses and the correct agent behavior for each. Could mention idempotency or read-only nature, but sufficient for a status check.

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

Conciseness5/5

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

Three sentences, each earning its place: first states purpose, second explains workflow usage, third lists status values. Front-loaded and no wasted words.

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

Completeness5/5

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

For a simple status-check tool with one parameter and no output schema, the description is fully complete. It covers all necessary information for an agent to use correctly.

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

Parameters4/5

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

The schema covers 100% of the one parameter. The description adds that the subscriptionKey comes from generate_model, adding meaningful context beyond the schema.

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

Purpose5/5

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

The description clearly specifies the verb ('checks the status'), the resource ('3D model generation process'), and distinguishes itself from sibling tools like generate_model and download_model by referencing the subscription_key and the workflow steps.

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

Usage Guidelines4/5

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

It provides clear when-to-use guidance: after generate_model, before download_model, and describes actions based on status outcomes. Does not explicitly state when not to use it, but the flow is well-defined.

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

create_directoryB

Create a new directory

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Path to the directory to create

TDQS

B3.1/5.0

Behavior2/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It does not specify whether intermediate directories are created, what happens if the directory already exists, or any permissions required. The simple description omits critical behavioral details.

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

Conciseness4/5

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

The description is a single, clear sentence with no unnecessary words. It is appropriate for a simple operation, though it could arguably be expanded slightly for completeness.

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

Completeness2/5

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

Given the lack of annotations and output schema, the description is insufficiently complete. It does not explain return values, error conditions, or path semantics (e.g., absolute vs relative), leaving gaps for an agent.

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

Parameters3/5

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

The schema provides 100% coverage for the single parameter 'path' with a clear description. The tool description adds no additional meaning beyond the schema, earning a baseline score of 3.

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

Purpose5/5

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

The description 'Create a new directory' uses a specific verb and resource, clearly distinguishing it from sibling tools like read_file, write_file, or list_directory which operate on files rather than directories.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives, such as when to create a directory versus using write_file for file creation. No prerequisites or conditions are mentioned.

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

download_modelD

show file to browse

ParametersJSON Schema

Name	Required	Description	Default
`task_uuid`	Yes	show file to browse

TDQS

D1.5/5.0

Behavior1/5

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

With no annotations, the description fails to disclose any behavioral traits such as whether this tool modifies state or requires authentication. It only says 'show file to browse', which is vague.

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?

The description is extremely short but under-specified, sacrificing clarity. Every sentence should earn its place; this one does not.

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?

Given no annotations, no output schema, and a vague description, the tool is severely incomplete. The agent lacks critical information for correct invocation.

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

Parameters3/5

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

Schema description coverage is 100%, but the parameter description 'show file to browse' adds no meaningful semantics beyond the tool description. Baseline 3 applies.

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?

The description 'show file to browse' contradicts the tool name 'download_model', which implies an action of downloading. It is misleading as it does not state that the tool downloads a model.

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

Usage Guidelines2/5

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

No usage context is provided. The description does not indicate when to use this tool over siblings like 'read_file' or 'list_directory'.

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

generate_modelA

Initiates the 3D model generation process. This tool sends a request to create a 3D model based on the provided prompt and parameters. The response includes a main uuid and subscription_key, which must be saved to continue tracking progress through the check_status tool. When the request is successfully sent, the system returns a 'Submitted' message along with information about the uuid and created jobs. Note that the model generation process may take time.

ParametersJSON Schema

Name	Required	Description
`prompt`	Yes	The prompt describing the 3D model to generate
`tier`	No	The tier of the model generation
`geometry_file_format`	No	The format of the generated model, default glb
`material`	No	The material type for the model
`quality`	No	The quality of the generated model
`use_hyper`	No	Whether to use hyperboolean operations
`mesh_mode`	No	The mesh mode for the model
`mesh_simplify`	No	Whether to simplify the mesh
`mesh_smooth`	No	Whether to smooth the mesh
`addons`	No	Additional options for model generation
`seed`	No	Random seed for model generation
`condition_mode`	No	Mode for multi-image processing
`TApose`	No	Control for human-like model generation
`bbox_condition`	No	ControlNet for maximum model size [Width, Height, Length]
`images`	No	Array of image paths to upload (max 5)

TDQS

A4/5.0

Behavior3/5

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

With no annotations provided, the description must fully disclose behavioral traits. It mentions the asynchronous nature ('may take time') and the need to save returned ids. However, it does not discuss rate limits, authentication requirements, error conditions, or resource costs. This is adequate but incomplete for a complex generation tool.

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

Conciseness5/5

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

The description is three sentences long, front-loading the main purpose and then explaining response and workflow. It is concise, with no redundant phrases, and every sentence contributes to understanding the tool's behavior and next steps.

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

Completeness4/5

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

Given 15 parameters and no output schema, the description adequately covers the tool's workflow: starting generation, saving the returned uuid and subscription_key, and using check_status for tracking. It could be improved by explicitly stating the asynchronous nature and mentioning that the output can be downloaded later via download_model. Overall, it provides sufficient context for an agent to use the tool correctly in a multi-step process.

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

Parameters3/5

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

The input schema has 100% coverage, with descriptions for all 15 parameters. The description adds minimal value beyond repeating that generation is based on 'prompt and parameters' and mentions image uploads (max 5) and bbox_condition briefly. Since the schema already documents parameters, the baseline is 3, and the description does not significantly enhance understanding of parameter usage.

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

Purpose5/5

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

The description clearly states that the tool initiates a 3D model generation process and sends a request. It specifies the action (create), the resource (3D model), and distinguishes from sibling tools like check_status (which tracks progress) and download_model (which retrieves the result). The verb 'initiates' and the mention of a 'main uuid and subscription_key' provide precise context.

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

Usage Guidelines4/5

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

The description explains that the response includes uuid and subscription_key which must be saved to continue tracking progress via the check_status tool. It also notes that generation may take time, guiding users to use check_status for updates. However, it does not explicitly state when not to use this tool or list alternatives for different scenarios, such as when immediate results are needed.

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

list_directoryC

List the contents of a directory

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Path to the directory to list

TDQS

C2.9/5.0

Behavior2/5

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

No annotations provided, so description must cover behavior. It only says 'list the contents' without specifying whether it returns files only, includes subdirectories, or handles non-existent paths. No safety or mutability info.

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

Conciseness4/5

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

Extremely concise single sentence with no wasted words. However, it may be under-specified for a tool with no annotations or output schema.

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

Completeness2/5

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

Given no annotations, output schema, or error handling info, the description is incomplete. It fails to explain output format, behavior with hidden files, or error cases (e.g., invalid path).

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

Parameters3/5

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

Schema description coverage is 100% for the single parameter 'path', which has a clear description. The tool description adds no extra meaning beyond the schema.

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

Purpose4/5

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

The description clearly states the tool lists directory contents, with a specific verb and resource. However, it does not differentiate from sibling tools like read_file or check_status, which are distinct but could be confused for similar operations.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives. No mention of prerequisites, directory existence, or cases where it should not be used.

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

read_fileB

Read the contents of a file

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Path to the file to read

TDQS

B3.1/5.0

Behavior2/5

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

No annotations provided, and description does not disclose important behaviors such as encoding handling, file size limits, or whether the entire file is read at once. Minimal transparency.

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

Conciseness4/5

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

Extremely concise single sentence, no wasted words. Could be slightly more structured with additional behavioral notes.

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

Completeness2/5

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

No output schema or annotations. Lacks details on return format, encoding, or error handling. Incomplete for a simple file read operation.

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

Parameters3/5

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

Schema coverage is 100%, so the description adds no extra meaning beyond the schema. Baseline 3 is appropriate as the parameter description is adequate but not enriched.

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

Purpose5/5

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

Description clearly states the tool reads the contents of a file with a specific verb and resource. It distinguishes from sibling tools like write_file and list_directory.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives. Lacks context for prerequisites or scenarios where other tools (e.g., download_model) would be more appropriate.

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

write_fileB

Write content to a file

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Path to the file to write
`content`	Yes	Content to write to the file

TDQS

B3.1/5.0

Behavior2/5

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

Missing annotations and description does not disclose critical behavior such as whether the file is overwritten or appended, or what happens if the file already exists.

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

Conciseness4/5

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

Extremely concise (4 words) and front-loaded, but could benefit from a slightly more detailed one-liner.

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

Completeness2/5

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

Given the lack of annotations and output schema, the description does not cover important aspects like return value, error conditions, or file handling behavior.

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

Parameters3/5

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

Schema coverage is 100%, so the description adds no additional meaning beyond what the schema provides; baseline of 3 is appropriate.

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

Purpose5/5

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

The description 'Write content to a file' clearly states the verb (write) and resource (file), and distinguishes from siblings like read_file.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives (e.g., read_file), and no mention of prerequisites or specific use cases.

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

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3/5.0

Disambiguation5/5

The tools are cleanly divided into two domains: 3D model generation (generate_model, check_status, download_model) and file system operations (create_directory, list_directory, read_file, write_file). Each tool has a distinct purpose with no overlap, making selection unambiguous.

Naming Consistency5/5

All tools follow a consistent verb_noun naming pattern (e.g., generate_model, check_status, list_directory). There are no deviations or mixed conventions, ensuring predictability.

Tool Count4/5

With 7 tools, the count is reasonable for a server that combines 3D model generation and auxiliary file operations. However, the file operations are slightly under-scoped (missing delete, rename), preventing a perfect score.

Completeness3/5

The 3D generation workflow (generate, check, download) is complete, but the file operations miss common actions like delete or rename. Additionally, the download_model tool's description is vague ('show file to browse'), leaving ambiguity about its exact functionality.

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Gessa: game asset generation for AI agents
ai.gessa
Generate game-ready 3D models, textures, and audio from natural language, over MCP.
AI & Machine Learning Image & Video Processing Audio Processing
1
VULK
io.github.devjoaocastro
Generate, edit, and deploy immersive 3D/WebGL web projects from any MCP assistant.
Developer Tools Multimedia Processing
27
AXIS Avatar Foundry A
com.jonathanarvay
3D avatar/asset foundry: text/image -> rigged, validated, engine-ready GLB via x402.
Image & Video Processing Games & Gamification AI & Machine Learning
142
Sceneplane
online.sceneplane
Cloud Blender for AI agents: scenes, assets, renders, MP4, STL, GLB — over hosted remote MCP.
Image & Video Processing Multimedia Processing
1

Related MCP Servers

Meshy MCP Serverofficial
AI & Machine Learning Design Tools
meshy-dev
A
license
Not graded
quality
B
maintenance
Enables AI agents to create, manage, and download 3D models, textures, images, rigged characters, and animations through natural conversation.
Updated 13 days ago (2026-08-22 16:16 UTC)
5,090
38
MIT
meshy-youtube-mcp
AI & Machine Learning Multimedia Processing Entertainment & Media
Scottcjn
A
license
A
quality
C
maintenance
Enables generating 3D models from text prompts, rendering turntable animations, and uploading them directly to YouTube via an MCP interface.
Updated 15 days ago (2026-08-20 03:11 UTC)
14
13
MIT
PicoBerry MCP Server
AI & Machine Learning Image & Video Processing Multimedia Processing
UModeler
A
license
A
quality
A
maintenance
Enables generating game-ready 3D models, images, and animations from any MCP client via PicoBerry's multi-engine API.
Updated 23 days ago (2026-08-12 14:08 UTC)
14
106
1
MIT
GoModelHub 3D MCPofficial
AI & Machine Learning Image & Video Processing
gomodelhub
A
license
Not graded
quality
C
maintenance
Enables 3D model generation via natural language, supporting text-to-3D and image-to-3D with remote or local deployment options.
Updated 15 days ago (2026-08-20 08:28 UTC)
MIT

Appeared in Searches

A search for information about 3D

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/Context3D/context3d-model-mcp-server'

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

Context3D - AI-Powered 3D Model Generation with MCP

🔍 Overview

Key Features of the Context3D Platform:

Key Features of this MCP Server:

🏗️ Technical Architecture

Core Context3D Cloud Service Pipeline (Detailed in plant.md)

MCP Server Communication Flow

Authentication Flow (within MCP Server)

MCP Integration Guide

Adding the MCP Server to Claude Desktop

Available Tools

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Meshy MCP Serverofficial

GoModelHub 3D MCPofficial

Appeared in Searches

Latest Blog Posts

MCP directory API