# Label Studio

> Use this tool when you need to programmatically manage data labeling projects, import tasks, and access annotations for AI model training. It solves problems related to data preparation and annotation workflow integration, providing a comprehensive interface for creating projects, retrieving data, and adding model predictions. It is ideal for teams building AI-powered labeling workflows, data scientists, and organizations integrating labeling into machine learning pipelines.

Canonical page: https://skillsregistry.net/skills/label-studio  
JSON: https://api.skillsregistry.net/v1/skills/label-studio

## Description

Label Studio MCP server by HumanSignal that provides AI assistants with programmatic access to Label Studio data labeling platform through the official label-studio-sdk. The implementation offers comprehensive project management capabilities including creating projects with XML labeling configurations, importing tasks from JSON files, and managing predictions, alongside task-level operations for retrieving data, annotations, and adding model predictions to specific tasks. Built with Python using FastMCP and requiring Label Studio API credentials, it serves teams building AI-powered labeling workflows, data scientists needing conversational access to annotation projects, and organizations integrating Label Studio into broader machine learning pipelines where natural language interaction with labeling infrastructure streamlines data preparation and model training processes.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/label-studio)
- **Repository:** <https://github.com/humansignal/label-studio-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "label-studio"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/label-studio` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/label-studio/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt