How do I connect my Scale AI account?

You subscribe to the MCP on Vinkius and enter your Scale AI Live API Key. Once connected, you can use it in any compatible client.

Which AI clients can I use with this MCP?

You can use this MCP with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

Can I cancel a task if I make a mistake?

Yes, you can use the cancel_task capability to stop a pending task and manage your budget.

What kind of data can I label?

The MCP supports image annotation, semantic segmentation, video playback, named entity recognition, and text collection.

Do I need to use the Scale AI web dashboard?

No, this MCP allows you to manage projects, batches, and tasks directly through your AI agent.

How do I start a high-volume labeling job using batches?

First, use create_batch to initialize a group for your project. After submitting your tasks to this batch, call finalize_batch to signal Scale to begin the labeling process.

Can I check the status of a specific annotation task?

Yes, use the get_task capability with the specific Task ID. It will return the full metadata, current status, and any available results for that unit of work.

What should I do if I submitted a task by mistake?

You can use the cancel_task capability with the Task ID. If you need to reuse the unique identifier, you can also set the clear_unique_id parameter to true.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Scale AI to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run large-scale labeling workflows through your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 11 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 11 available through Scale AI.

01
Cancel task
This capability stops a pending task. You can also clear the unique ID to make it available for reuse.
02
Create image annotation task
This capability generates a new image annotation task. Use it to send specific images for labeling.
03
Create named entity recognition task
This capability creates a Named Entity Recognition task. It is used for extracting specific entities from text.
04
Create segment annotation task
This capability starts a Semantic Segmentation task. Use this for pixel-level labeling requirements.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 11 available through Scale AI.

05
Create text collection task
This capability sets up a Text Collection task. It helps you gather specific text datasets.
06
Create video playback annotation task
This capability creates a Video Annotation task. Use it to label temporal data in video files.
07
Finalize batch
This capability finishes a batch. Once called, Scale AI begins processing the tasks within that batch.
08
Get task
This capability retrieves the details of a specific task. Use it to check the status or results of a single item.

Capability set03 / 03

09-11

3 capabilities in this set.

Part of 11 available through Scale AI.

09
Update project params
This capability modifies project-level instructions. You can use it to refine labeling quality dynamically.
10
Create batch
This capability creates a new batch. It allows you to group multiple tasks together for organized processing.
11
Create project
This capability initializes a new Scale project. You can define the labeling type during setup.

Real work

What teams actually run

Automated Edge Case Labeling

An engineer identifies a model failure and immediately sends the problematic images to Scale AI for annotation.

RLHF Pipeline Management

A researcher sets up a new project to gather human feedback for model fine-tuning.

Batch Processing Control

A data manager organizes thousands of tasks into batches and finalizes them to start the labeling process.

Dynamic Instruction Updates

A team realizes labeling quality is low and uses the agent to update project parameters instantly.

Automate a task

Put Scale AI to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Scale AI works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Scale AI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

916ms average. Fast in production.

Scale AI is checked daily against the live service.

Daily averagePeak 1191ms

Oct 3Today

Fastest day: 845ms
Slowest day: 1191ms
14-day trend: Improving-11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 11 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Scale AI, so you can see the experience inside your AI.

It does not authenticate your account with Scale AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Scale AI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_lsC40U9ook5OZ8hrmwvYLqntMTpGHdSfQWvhNSRl/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Scale AI capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "scale-ai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_lsC40U9ook5OZ8hrmwvYLqntMTpGHdSfQWvhNSRl/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Scale AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Scale AI owners hand off.

This MCP is designed for technical teams managing large-scale machine learning datasets.

01
ML Engineers
They use the agent to automate the submission of edge cases found during training.
02
Data Operations Managers
They monitor batch progress and update labeling instructions without leaving their chat interface.
03
AI Researchers
They spin up RLHF or annotation projects to validate new datasets quickly.

FAQ

Questions Scale AI owners ask.

01
How do I connect my Scale AI account?
You subscribe to the MCP on Vinkius and enter your Scale AI Live API Key. Once connected, you can use it in any compatible client.
02
Which AI clients can I use with this MCP?
You can use this MCP with any compatible client, including Claude, Cursor, Windsurf, and VS Code.
03
Can I cancel a task if I make a mistake?
Yes, you can use the cancel_task capability to stop a pending task and manage your budget.
04
What kind of data can I label?
The MCP supports image annotation, semantic segmentation, video playback, named entity recognition, and text collection.
05
Do I need to use the Scale AI web dashboard?
No, this MCP allows you to manage projects, batches, and tasks directly through your AI agent.
06
How do I start a high-volume labeling job using batches?
First, use create_batch to initialize a group for your project. After submitting your tasks to this batch, call finalize_batch to signal Scale to begin the labeling process.
07
Can I check the status of a specific annotation task?
Yes, use the get_task capability with the specific Task ID. It will return the full metadata, current status, and any available results for that unit of work.
08
What should I do if I submitted a task by mistake?
You can use the cancel_task capability with the Task ID. If you need to reuse the unique identifier, you can also set the clear_unique_id parameter to true.

Explore

More in AI Frontier

Connect Scale AI to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Cancel task

Create image annotation task

Create named entity recognition task

Create segment annotation task

05-08

Create text collection task

Create video playback annotation task

Finalize batch

Get task

09-11

Update project params

Create batch

Create project

What teams actually run

Automated Edge Case Labeling

RLHF Pipeline Management

Batch Processing Control

Dynamic Instruction Updates

Building your own app? The connector is yours to use.

Scale AI Connector

Claude Desktop

ML Engineers

Data Operations Managers

AI Researchers

How do I connect my Scale AI account?

Which AI clients can I use with this MCP?

Can I cancel a task if I make a mistake?

What kind of data can I label?

Do I need to use the Scale AI web dashboard?

How do I start a high-volume labeling job using batches?

Can I check the status of a specific annotation task?

What should I do if I submitted a task by mistake?

data.world AI Connector

Hevo Data (ETL & Data Pipeline) AI Connector

Alation AI Connector

Roboflow AI Connector

Suggestions

Data Pipeline Prover AI Connector

Data.gov Catalog AI Connector

AI Training Data Valuation Engine AI Connector

AI Data Labeling Cost Optimizer AI Connector