Skip to main content
Glama
enesjakozh
gregkop

Sketchfab MCP Server

by gregkop
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Sketchfab MCP Server

A Model Context Protocol (MCP) server for interacting with Sketchfab's 3D model platform. This MCP allows you to search, view details, and download 3D models from Sketchfab directly through Claude or Cursor.

Features

  • Search for 3D Models: Find models on Sketchfab using keywords, tags, and categories

  • View Model Details: Get comprehensive information about specific models

  • Download Models: Download models in various formats (gltf, glb, usdz, source)

Related MCP server: meshy-mcp

Prerequisites

  • Node.js 18 or higher

  • A Sketchfab API key (for authentication)

Installation

  1. Clone this repository

  2. Install dependencies:

    npm install

  3. Build the project:

    npm run build

Usage

Running the MCP Server

npm start

To provide your Sketchfab API key, use the --api-key parameter:

node build/index.js --api-key YOUR_API_KEY

Alternatively, you can set the SKETCHFAB_API_KEY environment variable:

export SKETCHFAB_API_KEY=YOUR_API_KEY
npm start

Available Tools

1. sketchfab-search

Search for 3D models on Sketchfab based on keywords and filters.

Parameters:

  • query (optional): Text search query (e.g., "car", "house", "character")

  • tags (optional): Filter by specific tags (e.g., ["animated", "rigged", "pbr"])

  • categories (optional): Filter by categories (e.g., ["characters", "architecture", "vehicles"])

  • downloadable (optional): Set to true to show only downloadable models

  • limit (optional): Maximum number of results to return (1-24, default: 10)

2. sketchfab-model-details

Get detailed information about a specific Sketchfab model.

Parameters:

  • modelId: The unique ID of the Sketchfab model

3. sketchfab-download

Download a 3D model from Sketchfab.

Parameters:

  • modelId: The unique ID of the Sketchfab model to download

  • format (optional): Preferred format to download the model in (gltf, glb, usdz, source)

  • outputPath (optional): Local directory or file path to save the downloaded file

Using with Cursor

  1. Go to Cursor Settings -> MCP -> Add new MCP server

  2. Configure your MCP:

    • Name: Sketchfab MCP

    • Type: command

    • Command: node /path/to/build/index.js --api-key YOUR_API_KEY

Using with Claude Desktop

Add the following MCP config to your Claude Desktop configuration:

{
  "mcpServers": {
    "sketchfab": {
      "command": "node",
      "args": ["/path/to/build/index.js", "--api-key", "YOUR_API_KEY"]
    }
  }
}

Environment Variables

You can set the following environment variables:

  • SKETCHFAB_API_KEY: Your Sketchfab API key (alternative to passing it with the --api-key parameter)

License

ISC

Available Tools

4 tools
sample-toolC

A sample tool for demonstration purposes

ParametersJSON Schema
NameRequiredDescriptionDefault
inputYesInput parameter for the sample tool

TDQS

C2.3/5.0
Behavior1/5

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

The description provides zero behavioral information beyond the name. With no annotations provided, the description carries the full burden of disclosing behavioral traits like whether this is a read or write operation, what side effects it might have, authentication requirements, or rate limits. The description fails to address any of these aspects, leaving the agent completely in the dark about how this tool behaves.

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 extremely concise at just one sentence with no wasted words. It's appropriately sized for what little information it conveys, and while it's under-specified, it's not verbose or poorly structured. Every word in 'A sample tool for demonstration purposes' serves its purpose within the minimal context provided.

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 that this is a tool with one parameter, no annotations, no output schema, and no sibling tools, the description is incomplete. It fails to explain what the tool actually does, what behavior to expect, or what context it operates in. While the simplicity of the tool might lower expectations, the description doesn't provide enough information for an agent to understand when and how to use it effectively.

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?

With 100% schema description coverage and only one parameter documented in the schema, the description adds no additional parameter information. The schema already describes the 'input' parameter as 'Input parameter for the sample tool,' so the description doesn't compensate or add meaning beyond what's in the structured data. This meets the baseline of 3 when schema coverage is high.

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

Purpose2/5

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

The description 'A sample tool for demonstration purposes' is a tautology that essentially restates the tool name 'sample-tool' without specifying what it actually does. It doesn't mention any specific verb or resource, nor does it explain what kind of demonstration it performs. While it's not misleading, it provides minimal functional information beyond the name itself.

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?

The description provides no guidance on when to use this tool, what context it's appropriate for, or what alternatives might exist. With no sibling tools mentioned, there's no need for differentiation, but the description fails to establish any usage context whatsoever. It doesn't indicate whether this is for testing, learning, or any specific scenario.

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

sketchfab-downloadB

Download a 3D model from Sketchfab

ParametersJSON Schema
NameRequiredDescriptionDefault
modelIdYesThe unique ID of the Sketchfab model to download (must be downloadable)
formatNoPreferred format to download the model in (defaults to gltf if available)
outputPathNoLocal directory or file path to save the downloaded file (will use temp directory if not specified)

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 full burden for behavioral disclosure. It only says 'download' but does not specify that the tool may overwrite files, requires network access, or what happens if the model is not downloadable or the format is unavailable.

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 concise sentence with no wasted words. However, it could include a few more details without becoming verbose, such as indicating the output is a file.

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?

Missing important context: no description of return value (e.g., saved file path), no error handling info, and no note about whether the tool checks for model availability before downloading. Despite having only 3 parameters, the description is too minimal for safe agent use.

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 each parameter has a description. The tool description adds no additional meaning beyond what is in the schema. The default behavior for format and outputPath is already stated in 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 states 'Download a 3D model from Sketchfab', which is a specific verb+resource combination and distinguishes it from sibling tools that list categories, licenses, search, or get model details.

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 prerequisites (e.g., model must be downloadable), and no context about the required modelId coming from a search or list tool.

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

sketchfab-model-detailsB

Get detailed information about a specific Sketchfab model

ParametersJSON Schema
NameRequiredDescriptionDefault
modelIdYesThe unique ID of the Sketchfab model (found in URLs or search results)

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations, the description carries full burden but only says 'detailed information' without explaining what behavior to expect (e.g., does it require authentication? Are there rate limits?). It lacks behavioral context.

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?

Single sentence, 9 words, no fluff. Front-loaded with the action, efficient for a simple tool.

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 exists, and the description does not hint at what 'detailed information' includes (e.g., metadata, stats, file URLs). For a tool returning model details, the description should outline the scope of the response.

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% and the parameter description is informative. The tool description does not add additional semantic meaning beyond what the schema already provides, so baseline score 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 clearly states the action ('Get detailed information') and resource ('specific Sketchfab model'). It is distinct from sibling tools like sketchfab-search (list) and sketchfab-download (file retrieval).

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 explicit guidance on when to use this tool versus alternatives. The description does not mention prerequisites, limitations, or cases where another sibling tool 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.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updates
    • First observedsample-tool
    • First observedsketchfab-download
    • First observedsketchfab-model-details
    • First observedsketchfab-search
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.7/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: sample-tool is for demonstration, sketchfab-download handles downloading models, sketchfab-model-details retrieves model information, and sketchfab-search performs searches. There is no overlap in functionality, making tool selection straightforward for an agent.

Naming Consistency4/5

Three of the four tools follow a consistent 'sketchfab-' prefix and hyphenated naming pattern (e.g., sketchfab-download, sketchfab-model-details, sketchfab-search), which is predictable and readable. The outlier is sample-tool, which deviates from this pattern, but the overall set remains mostly consistent.

Tool Count4/5

With 4 tools, the count is reasonable for a Sketchfab server, covering core operations like search, details, and download. It is slightly lean but functional; adding tools like model upload or user management could enhance it, but it's not incomplete for basic use.

Completeness3/5

The tools cover key operations for interacting with Sketchfab models: search, get details, and download. However, there are notable gaps such as uploading models, managing user accounts, or handling collections, which limits full lifecycle coverage. The sample-tool adds no functional value to the domain.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches