Label Studio MCP Server
HumanSignal/label-studio-mcp-server
Automação de anotação e gestão de dados Label Studio via Claude
Ver no GitHubServidor MCP que integra Label Studio com Claude, permitindo gerenciamento programático de projetos, tarefas e predições via linguagem natural. Facilita automação de fluxos de anotação de dados e treinamento de modelos diretamente através de conversas com o Claude.
Instalação
npx convez-ai HumanSignal/label-studio-mcp-server1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Automatizar criação e configuração de projetos de anotação
- Consultar status de tarefas e predições em projetos RAG/ML
- Importar dados e adicionar predições de modelos programaticamente
- Integrar anotação de dados em pipelines de treinamento contínuo
Veredito

Excelente ponte entre Claude e Label Studio para quem trabalha com anotação de dados em escala. Reduz fricção em fluxos repetitivos de labeling, mas exige Label Studio já instalado e configurado — não é solução standalone.
README
A tradução para o português deste README ainda está na fila.
Label Studio MCP Server
Overview
This project provides a Model Context Protocol (MCP) server that allows interaction with a Label Studio instance using the label-studio-sdk. It enables programmatic management of labeling projects, tasks, and predictions via natural language or structured calls from MCP clients. Using this MCP Server, you can make requests like:
- "Create a project in label studio with this data ..."
- "How many tasks are labeled in my RAG review project?"
- "Add predictions for my tasks."
- "Update my labeling template to include a comment box."
Features
- Project Management: Create, update, list, and view details/configurations of Label Studio projects.
- Task Management: Import tasks from files, list tasks within projects, and retrieve task data/annotations.
- Prediction Integration: Add model predictions to specific tasks.
- SDK Integration: Leverages the official
label-studio-sdkfor communication.
Prerequisites
- Running Label Studio Instance: You need a running instance of Label Studio accessible from where this MCP server will run.
- API Key: Obtain an API key from your user account settings in Label Studio.
Configuration
The MCP server requires the URL and API key for your Label Studio instance. If launching the server via an MCP client configuration file, you can specify the environment variables directly within the server definition. This is often preferred for client-managed servers.
Add the following JSON entry to your claude_desktop_config.json file or Cursor MCP settings:
{
"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", // <-- Your API key
"LABEL_STUDIO_URL": "http://localhost:8080"
}
}
}
}
Tools
The MCP server exposes the following tools:
Project Management
get_label_studio_projects_tool(): Lists available projects (ID, title, task count).get_label_studio_project_details_tool(project_id: int): Retrieves detailed information for a specific project.get_label_studio_project_config_tool(project_id: int): Fetches the XML labeling configuration for a 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 including a URL.update_label_studio_project_config_tool(project_id: int, new_label_config: str): Updates the XML labeling configuration for an existing project.
Task Management
list_label_studio_project_tasks_tool(project_id: int): Lists task IDs within a project (up to 100).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 (containing a list of task objects) into a project. Returns import summary and project URL.
Predictions
create_label_studio_prediction_tool(task_id: int, result: List[Dict[str, Any]], ...): Creates a prediction for a specific task. Requires the prediction result as a list of dictionaries matching the Label Studio format. Optionalmodel_versionandscore.
Example Use Case
- Create a new project using
create_label_studio_project_tool. - Prepare a JSON file (
tasks.json) with task data. - Import tasks using
import_label_studio_project_tasks_tool, providing the project ID from step 1 and the path totasks.json. - List task IDs using
list_label_studio_project_tasks_tool. - Get data for a specific task using
get_label_studio_task_data_tool. - Generate a prediction result structure (list of dicts).
- Add the prediction using
create_label_studio_prediction_tool.
Contact
For questions or support, reach out via GitHub Issues.