Label Studio
๐๏ธ ๐ โ๏ธ ๐ช ๐ง ๐ - Create, manage, and automate Label Studio projects, tasks, and predictions for data labeling workflows.
What is Label Studio?
Label Studio is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ๐๏ธ ๐ โ๏ธ ๐ช ๐ง ๐ - create, manage, and automate label studio projects, tasks, and predictions for data labeling workflows.
๐๏ธ ๐ โ๏ธ ๐ช ๐ง ๐ - Create, manage, and automate Label Studio projects, tasks, and predictions for data labeling workflows.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- ๐๏ธ ๐ โ๏ธ ๐ช ๐ง ๐ - Create, manage, and automate Label Studio pr
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx label-studio-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Label Studio
The Label Studio MCP server connects AI assistants to Label Studio, the open-source data annotation platform, enabling natural language management of labeling projects, tasks, and ML predictions. You can create projects with custom labeling templates, import datasets, retrieve annotation results, and add model predictions to tasks โ all from a conversational interface. This makes it practical to automate dataset preparation and annotation pipeline management as part of ML model training workflows.
Prerequisites
- A running Label Studio instance (self-hosted at e.g. http://localhost:8080 or cloud-hosted)
- A Label Studio API key from your user Account & Settings page
- uv or uvx installed (pip install uv) for running the server
- An MCP-compatible client such as Claude Desktop or Cursor
Ensure Label Studio is running
The MCP server communicates with a Label Studio instance over HTTP. Start your local instance or note the URL of your cloud instance before proceeding.
# Start a local Label Studio instance (if not already running)
pip install label-studio
label-studio startRetrieve your Label Studio API key
Log in to Label Studio, navigate to Account & Settings (top-right menu), and copy your personal API key from the Access Token section.
Configure Claude Desktop
Add the Label Studio MCP server to your Claude Desktop config using uvx to run directly from the GitHub repository, with your API key and instance URL as environment variables.
{
"mcpServers": {
"label-studio": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/HumanSignal/label-studio-mcp-server",
"mcp-label-studio"
],
"env": {
"LABEL_STUDIO_API_KEY": "your-api-key-here",
"LABEL_STUDIO_URL": "http://localhost:8080"
}
}
}
}Restart Claude Desktop
Restart Claude Desktop to load the new server configuration. The Label Studio tools will appear in Claude's tool list.
Verify the connection
Ask Claude to list your Label Studio projects to confirm it can reach your instance with the provided API key.
Label Studio Examples
Client configuration
Claude Desktop configuration running the Label Studio MCP server via uvx with API credentials as environment variables.
{
"mcpServers": {
"label-studio": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/HumanSignal/label-studio-mcp-server",
"mcp-label-studio"
],
"env": {
"LABEL_STUDIO_API_KEY": "YOUR_LABEL_STUDIO_API_KEY",
"LABEL_STUDIO_URL": "http://localhost:8080"
}
}
}
}Prompts to try
Data labeling workflow tasks you can run from Claude once the server is connected.
- "List all my Label Studio projects and how many tasks each has"
- "Create a new image classification project called 'Cat vs Dog Classifier'"
- "Import the tasks from /path/to/dataset.json into my project ID 3"
- "How many tasks in project 5 have been annotated so far?"
- "Add a prediction to task 42 in project 3 with label 'cat' and confidence 0.95"
- "Show me the annotation results for task ID 100"Troubleshooting Label Studio
Connection refused when the server tries to reach Label Studio
Verify that LABEL_STUDIO_URL points to a running Label Studio instance. For local instances, confirm Label Studio is started on the expected port (default 8080). For Docker deployments, use the container's network address rather than localhost if the MCP server runs outside Docker.
401 Unauthorized errors when calling tools
Your LABEL_STUDIO_API_KEY may be invalid or expired. Go to Label Studio Account & Settings and generate a new token. Paste the new token into your MCP client config env block and restart the client.
uvx fails to install from GitHub with network or build errors
Ensure uv is up to date (pip install --upgrade uv). If the GitHub URL is unreachable, clone the repository manually, run 'pip install -e .' inside it, then change the command in your config to 'python' with args ['-m', 'mcp_label_studio'] and adjust the path accordingly.
Frequently Asked Questions about Label Studio
What is Label Studio?
Label Studio is a Model Context Protocol (MCP) server that ๐๏ธ ๐ โ๏ธ ๐ช ๐ง ๐ - create, manage, and automate label studio projects, tasks, and predictions for data labeling workflows. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Label Studio?
Follow the installation instructions on the Label Studio GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Label Studio?
Label Studio works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Label Studio free to use?
Yes, Label Studio is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
Label Studio Alternatives โ Similar Data Science & ML Servers
Looking for alternatives to Label Studio? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
โ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
โ 3.1k๐ ๐ - MCP server that exposes RocketRide AI pipelines as t
Aix Db
โ 2.1kAix-DB ๅบไบ LangChain/LangGraph ๆกๆถ๏ผ็ปๅ MCP Skills ๅคๆบ่ฝไฝๅไฝๆถๆ๏ผๅฎ็ฐ่ช็ถ่ฏญ่จๅฐๆฐๆฎๆดๅฏ็็ซฏๅฐ็ซฏ่ฝฌๆขใ
NeMo Data Designer
โ 1.9k๐จ NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
โ 1.7kOpen source implementation and extension of Google Researchโs PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
โ 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 Label Studio 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 Label Studio?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.