MCP Server - Labellerr Documentation

Introduction

The Labellerr MCP Server enables seamless interaction with the Labellerr platform using natural language through AI assistants such as Claude Desktop and Cursor. Built on the Model Context Protocol (MCP), it provides 23 comprehensive tools for managing datasets, projects, annotations, and exports through conversational interfaces.

Quick Start

Prerequisites

Python 3.8 or higher
Git installed on your system
Labellerr API credentials (API Key, API Secret, Client ID) - Get your credentials
Claude Desktop or Cursor installed

Installation

First, clone the SDKPython repository:

Clone Repository

git clone https://github.com/Labellerr/SDKPython.git
cd SDKPython

Then install the required dependencies:

Install Dependencies

pip install -r requirements.txt

Configuration

Cursor
Claude Desktop

Add to ~/.cursor/mcp.json:

Cursor Configuration

{
  "mcpServers": {
    "labellerr": {
      "command": "python3",
      "args": ["/FULL/PATH/TO/SDKPython/labellerr/mcp_server/server.py"],
      "env": {
        "LABELLERR_API_KEY": "your_api_key",
        "LABELLERR_API_SECRET": "your_api_secret",
        "LABELLERR_CLIENT_ID": "your_client_id"
      }
    }
  }
}

Add to Claude Desktop config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Claude Desktop Configuration

{
  "mcpServers": {
    "labellerr": {
      "command": "python3",
      "args": ["/FULL/PATH/TO/SDKPython/labellerr/mcp_server/server.py"],
      "env": {
        "LABELLERR_API_KEY": "your_api_key",
        "LABELLERR_API_SECRET": "your_api_secret",
        "LABELLERR_CLIENT_ID": "your_client_id"
      }
    }
  }
}

Important: Use the absolute path to server.py. Restart your AI assistant completely after configuration.

Available Tools

The MCP server provides 23 comprehensive tools organized into 5 functional categories to manage your complete annotation workflow:

Project Management (4 tools)

tool

Create a new annotation project (requires dataset_id and template_id)

tool

List all projects in your workspace

tool

Get detailed information about a specific project

tool

Update annotation rotation configuration

Dataset Management (5 tools)

tool

Create dataset with automatic file upload and status polling

tool

Upload individual files to create a dataset

tool

Upload an entire folder of files

tool

List all datasets with filtering options

tool

Get detailed information about a dataset

Annotation Operations (6 tools)

tool

Create annotation template with questions/guidelines

tool

Export project annotations in various formats (JSON, COCO, CSV, PNG)

tool

Check status of export jobs

tool

Get download URL for completed exports

tool

Upload pre-annotations (synchronous)

tool

Upload pre-annotations (asynchronous)

Monitoring Tools (4 tools)

tool

Check MCP server health and connection status

tool

List all active operations and their status

tool

Get progress statistics for a project

tool

Monitor background job status

Query Tools (4 tools)

tool

Get detailed statistics for a project

tool

Get detailed information about a dataset

tool

Query history of operations performed

tool

Search for projects by name or type

Usage Examples

Interact with the MCP server using natural language commands through your AI assistant. Below are common usage patterns:

Create a Complete Project

Create an image annotation project called "Product Detection" with 
bounding boxes for "Product" and "Defect". Upload images from 
/Users/me/products and use my email user@example.com

Automated workflow:

Upload images from the specified folder
Create a dataset with uploaded files
Generate an annotation template with bounding box questions
Create and link the project with all resources

Monitor Project Progress

What's the progress on all my annotation projects?

Export Annotations

Export all accepted annotations from project abc123 in COCO JSON format

Upload Additional Data

Upload images from /Users/me/more-data to dataset xyz789

Project Creation Workflow

The MCP server implements a structured three-step workflow for creating annotation projects. When you request a complete project, the server automatically executes all steps in sequence.

Automated Workflow: Describe your requirements in natural language, and the MCP server handles the complete workflow automatically.

Step 1: Create Dataset

The server uploads your files and creates a dataset.Process:

Files are uploaded to cloud storage
Dataset is created and linked
Processing status is monitored until completion

Example request:

Create a dataset called "Training Data" from folder /path/to/images

Server response:

Uploaded 150 images
Dataset created: dataset_abc123
Dataset ready for annotation

Step 2: Create Template

The server creates an annotation template with your specified questions.Process:

Annotation questions are defined
Question types are configured (BoundingBox, polygon, etc.)
Template is validated and saved

Example request:

Create an annotation template with bounding boxes for "Car" and "Truck"

Server response:

Template created: template_xyz789
Questions: Car (BoundingBox), Truck (BoundingBox)

Step 3: Create Project

The server links the dataset and template to create your project.Process:

Dataset and template are validated
Project is created with proper configuration
Resources are linked and ready for annotation

Example request:

Create a project using dataset dataset_abc123 and template template_xyz789

Server response:

Project created: project_final_456
Linked dataset: dataset_abc123 (150 files)
Linked template: template_xyz789
Ready to start annotation

Unified Command: You can create everything in one natural language request:

Create an image annotation project called "Vehicle Detection" with 
bounding boxes for "Car" and "Truck". Upload images from 
/Users/me/vehicles and use my email user@example.com

The MCP server will automatically execute all three steps and provide you with the final project ID.

Workflow Benefits:

Proper resource management
Clear project structure
Validation at each step
Automatic error handling

Supported Data Types

The MCP server supports the following data types across all tools:

Data Type	Supported Formats
Image	JPG, PNG, TIFF
Video	MP4
Audio	MP3, WAV
Document	PDF
Text	TXT

Export Formats

Annotations can be exported in multiple industry-standard formats:

Format	Description
json	Labellerr native format with complete annotation metadata
coco_json	COCO dataset format for computer vision tasks
csv	Comma-separated values for tabular data analysis
png	Segmentation masks for pixel-level annotations

Error Handling

The MCP server provides descriptive error messages to help diagnose and resolve issues:

Error: dataset_id is required
Message: Please create a dataset first using dataset_upload_folder

All operations are logged in the operation history and can be queried using natural language:

Show me the history of operations I've performed

Troubleshooting

AI Assistant Doesn’t Show Tools

Resolution steps:

Completely restart your AI assistant (quit and reopen the application)
Verify the path to server.py is absolute (starts with / on macOS/Linux or C:\ on Windows)
Test the server manually: python3 /path/to/server.py
Check the MCP configuration file for syntax errors

Authentication Errors

Resolution steps:

Obtain fresh credentials from your Labellerr workspace
Update the configuration file with the correct API credentials
Ensure all three credentials (API Key, API Secret, Client ID) are present
Restart your AI assistant after updating credentials

File Upload Issues

Common causes and solutions:

Verify file paths are absolute, not relative
Check file system permissions for read access
Confirm file formats match the specified data type
Ensure sufficient disk space for upload operations

Advanced Features

Operation History

The server maintains a comprehensive log of all operations with timestamps, durations, and status information. Query the operation history using natural language:

Show me failed operations from the last hour

Resource Caching

Active projects and datasets are cached in memory for improved performance and faster access. View currently cached resources:

What Labellerr resources are currently active?

Status Polling

Dataset creation includes automatic status polling to monitor processing completion. Configure timeout settings as needed:

dataset_create(
  folder_path="/path/to/data",
  wait_for_processing=True,
  processing_timeout=300  # 5 minutes
)

Additional Resources

For comprehensive documentation and technical references:

GitHub Repository - Source code and examples
MCP Server README - Detailed server documentation

Next Steps

SDK Documentation

Learn about the Python SDK for programmatic access

Create Projects

Detailed guide on creating annotation projects

Export Data

Learn how to export your annotated data

Cookbooks

Practical examples and tutorials

​Introduction

​Quick Start

​Prerequisites

​Installation

​Configuration

​Available Tools

​Usage Examples

​Create a Complete Project

​Monitor Project Progress

​Export Annotations

​Upload Additional Data

​Project Creation Workflow

​Supported Data Types

​Export Formats

​Error Handling

​Troubleshooting

​AI Assistant Doesn’t Show Tools

​Authentication Errors

​File Upload Issues

​Advanced Features

​Operation History

​Resource Caching

​Status Polling

​Additional Resources

​Next Steps

SDK Documentation

Create Projects

Export Data

Cookbooks

Introduction

Quick Start

Prerequisites

Installation

Configuration

Available Tools

Usage Examples

Create a Complete Project

Monitor Project Progress

Export Annotations

Upload Additional Data

Project Creation Workflow

Supported Data Types

Export Formats

Error Handling

Troubleshooting

AI Assistant Doesn’t Show Tools

Authentication Errors

File Upload Issues

Advanced Features

Operation History

Resource Caching

Status Polling

Additional Resources

Next Steps