Label Studio MCP Server

What does “Label Studio” MCP Server do?

The Label Studio MCP Server is a Model Context Protocol (MCP) server that enables seamless integration of AI assistants with a Label Studio instance. Leveraging the label-studio-sdk, it allows programmatic management of labeling projects, tasks, and predictions via natural language or structured calls from MCP clients. This server empowers developers and AI agents to efficiently create and manage projects, import and query tasks, and automate predictions, all through standardized MCP tools. By exposing Label Studio’s core functionalities, it streamlines labeling workflows and enhances productivity for data annotation, quality review, and machine learning operations.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

No explicit MCP resources are listed in the repository documentation.

List of Tools

• get_label_studio_projects_tool()
  Lists available projects, returning ID, title, and task count for each project.
• get_label_studio_project_details_tool(project_id: int)
  Retrieves detailed information for a specified project.
• get_label_studio_project_config_tool(project_id: int)
  Fetches the XML labeling configuration for a given project.
• create_label_studio_project_tool(title: str, label_config: str, …)
  Creates a new project with a title, XML config, and optional settings; returns project details and URL.
• update_label_studio_project_config_tool(project_id: int, new_label_config: str)
  Updates the XML labeling configuration for an existing project.
• list_label_studio_project_tasks_tool(project_id: int)
  Lists up to 100 task IDs within a project.
• get_label_studio_task_data_tool(project_id: int, task_id: int)
  Retrieves the data payload for a specific task.
• get_label_studio_task_annotations_tool(project_id: int, task_id: int)
  Fetches existing annotations for a specific task.
• import_label_studio_project_tasks_tool(project_id: int, tasks_file_path: str)
  Imports tasks from a JSON file into a project; returns import summary and project URL.
• create_label_studio_prediction_tool(task_id: int, result: List[Dict[str, Any]], …)
  Creates a prediction for a specific task, with options for model version and score.

Use Cases of this MCP Server

• Automated Project Management
  Create, update, and configure labeling projects programmatically, streamlining setup and maintenance for large annotation operations.
• Bulk Task Import and Management
  Import tasks from files and manage them in bulk, enabling efficient data ingestion into Label Studio and easy retrieval of task data or annotations.
• Prediction Integration
  Add model predictions directly to tasks, facilitating ML-assisted annotation workflows and human-in-the-loop model evaluation.
• Quality Assurance and Metrics
  Query project details and task counts to monitor progress and quality across multiple labeling projects.
• Customized Annotation Templates
  Automate updates to annotation templates (label configs) for evolving project requirements, ensuring consistency and flexibility.

How to set it up

Windsurf

1. Ensure you have a running Label Studio instance and obtain your API key.
2. Open the Windsurf MCP server configuration file.
3. Add the Label Studio MCP server definition using the following JSON snippet:

   {
       "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_actual_api_key_here",
                   "LABEL_STUDIO_URL": "http://localhost:8080"
               }
           }
       }
   }
   

4. Save changes and restart Windsurf.
5. Verify the connection to your Label Studio instance.

Claude

1. Ensure Label Studio is running and you have your API key.
2. Locate your claude_desktop_config.json file.
3. Add the Label Studio MCP server configuration:

   {
       "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_actual_api_key_here",
                   "LABEL_STUDIO_URL": "http://localhost:8080"
               }
           }
       }
   }
   

4. Save and restart the Claude client.
5. Confirm successful setup in the client interface.

Cursor

1. Start with a running Label Studio and obtain your API key.
2. Open Cursor MCP settings.
3. Add this MCP server configuration JSON:

   {
       "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_actual_api_key_here",
                   "LABEL_STUDIO_URL": "http://localhost:8080"
               }
           }
       }
   }
   

4. Save and restart Cursor.
5. Check that the MCP server is accessible from Cursor.

Cline

1. Make sure Label Studio is up and running and note your API key.
2. Edit the Cline MCP server config file.
3. Insert the server entry as below:

   {
       "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_actual_api_key_here",
                   "LABEL_STUDIO_URL": "http://localhost:8080"
               }
           }
       }
   }
   

4. Save your changes and restart Cline.
5. Test connectivity to Label Studio via Cline.

Note:
Securely store your API key using environment variables as shown in the env section above. This keeps sensitive information out of source code and config files.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "label-studio": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change "label-studio" to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between the two tables:
This MCP server provides strong tool coverage for Label Studio management and clear setup documentation, but lacks prompt templates and explicit resource definitions. Sampling and roots support are not mentioned. Overall, it’s a solid but basic implementation for dedicated data labeling workflows.

MCP Score