ModelScope
ModelScope's official MCP Server (in active development).
What is ModelScope?
ModelScope is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to modelscope's official mcp server (in active development).
ModelScope's official MCP Server (in active development).
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- ModelScope's official MCP Server (in active development).
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx modelscopeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ModelScope
ModelScope MCP Server is the official MCP server from the ModelScope team that gives AI agents and chatbots direct access to ModelScope's ecosystem of AI resources. It supports AI image generation (text-to-image and image-to-image), searching and discovering models, datasets, studios (AI apps), research papers, and other MCP servers on the ModelScope platform. It is actively developed and installable via uvx, with Docker image support, making it easy to integrate into any MCP-compatible client.
Prerequisites
- A ModelScope account with an API token (sign up free at modelscope.cn)
- Python 3.10 or higher, or uv/uvx installed for the recommended install method
- Docker if you prefer the container-based deployment
- An MCP-compatible client such as Claude Desktop, Cursor, Cherry Studio, or VS Code
Get your ModelScope API token
Sign in to modelscope.cn, then navigate to Home → Access Tokens to retrieve or create your API token. This token authenticates all requests to the ModelScope API.
Install uv (recommended)
The server is designed to be run with uvx, which is part of the uv toolchain. Install it if you do not have it already.
curl -LsSf https://astral.sh/uv/install.sh | shAdd the server to your MCP client
Add the ModelScope MCP server configuration to your MCP client config file, providing your API token as the MODELSCOPE_API_TOKEN environment variable.
Alternatively, run with Docker
Use the pre-built Docker image if you prefer containerized deployment. Pass your API token as an environment variable.
docker run --rm -i \
-e MODELSCOPE_API_TOKEN=your-api-token \
ghcr.io/modelscope/modelscope-mcp-serverTest image generation
Ask your AI assistant to generate an image using ModelScope's text-to-image capability to confirm the server is working.
ModelScope Examples
Client configuration
Add this to your MCP client config (e.g., claude_desktop_config.json or ~/.cursor/mcp.json). Replace the token with your actual ModelScope API token.
{
"mcpServers": {
"modelscope-mcp-server": {
"command": "uvx",
"args": ["modelscope-mcp-server"],
"env": {
"MODELSCOPE_API_TOKEN": "your-api-token-here"
}
}
}
}Prompts to try
Explore ModelScope's AI resources and generate images through natural language.
- "Search ModelScope for text-to-image models and list the top 5 results."
- "Generate an image of a sunset over the ocean using ModelScope."
- "Find datasets on ModelScope related to natural language processing."
- "Search for ModelScope studios (AI apps) that do image segmentation."
- "Look up the latest research papers on ModelScope about diffusion models."Troubleshooting ModelScope
Authentication error: MODELSCOPE_API_TOKEN is invalid or missing
Verify the token is set correctly in your MCP client's env block. Tokens are found at modelscope.cn under Home → Access Tokens. Create a new token if the existing one has been revoked.
uvx command not found when starting the server
Install uv with the official installer: curl -LsSf https://astral.sh/uv/install.sh | sh. Then restart your terminal. Alternatively, use the Docker image which has no Python/uv dependency.
Image generation returns an error or empty result
Image generation is an active feature that depends on AIGC model availability on ModelScope. Try a simpler prompt or check the ModelScope status page. Ensure your API token has the necessary permissions for AIGC features.
Frequently Asked Questions about ModelScope
What is ModelScope?
ModelScope is a Model Context Protocol (MCP) server that modelscope's official mcp server (in active development). It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ModelScope?
Follow the installation instructions on the ModelScope GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with ModelScope?
ModelScope works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ModelScope free to use?
Yes, ModelScope is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
ModelScope Alternatives — Similar Data Science & ML Servers
Looking for alternatives to ModelScope? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up ModelScope in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use ModelScope?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.