Scale Ai MCP server

Connect Scale Ai to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

What you can do with the Scale Ai MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the update task tool in Scale Ai
  • Use the get batch tool in Scale Ai
  • Use the create batch tool in Scale Ai
  • Use the list projects tool in Scale Ai
  • Use the resend task callback tool in Scale Ai
  • Use the cancel task tool in Scale Ai

Supported Tools

update_task

Update Task

Update a Scale AI task's metadata, tags, or deduplication identifier. Supports replacing metadata and adding, replacing, or removing tags.

get_batch

Get Batch

Retrieve details and status for a specific Scale AI batch, including task completion progress.

create_batch

Create Batch

Create a batch within a Scale AI project to organize tasks by dataset or submission. Rapid and Studio batches must be finalized before their tasks can be worked on.

list_projects

List Projects

List all annotation projects in your Scale AI account. Optionally filter by archive status.

resend_callback

Resend Task Callback

Re-trigger the completion callback for a completed or errored Scale AI task. Useful when the original callback delivery failed or when you need to re-process the result.

cancel_task

Cancel Task

Cancel a pending Scale AI task. Only tasks with status `pending` (queued, not yet in progress) can be canceled. Calling cancel on an already canceled task is idempotent.

finalize_batch

Finalize Batch

Finalize a Scale AI batch so its tasks are sent to annotators. For Rapid/Studio projects, batches must be finalized before work begins. Optionally set the batch priority.

list_batches

List Batches

List batches in Scale AI, optionally filtered by project and status. Supports pagination and can include detailed progress information.

update_project

Update Project

Update a Scale AI project's default task parameters and instructions. Project-level parameters apply to future tasks.

list_tasks

List Tasks

List and filter annotation tasks in Scale AI. Supports filtering by project, batch, status, type, tags, review status, and date ranges. Results are paginated using token-based pagination.

get_task

Get Task

Retrieve full details for a specific Scale AI task by ID, including its status, response (if completed), metadata, and audit information.

manage_team

Manage Team

Manage Scale AI Studio team members. List current teammates, invite new members, or update existing member roles.

get_project

Get Project

Retrieve details for a specific Scale AI annotation project by name.

import_file

Import File

Import a file from a URL into Scale AI. Returns an attachment URL (prefixed with `scaledata://`) that can be used when creating tasks.

create_evaluation_task

Create Evaluation Task

Create an evaluation task for a Scale Rapid project using known answers to measure annotator quality. Requires an expected response and optionally an initial response for review-phase evaluations.

create_task

Create Task

Create a new annotation task in Scale AI. Supports all task types including image annotation, video annotation, text collection, document transcription, LiDAR annotation, and more. The task type determines which parameters are required.

create_project

Create Project

Create a new annotation project in Scale AI. A project is tied to one specific task type and use case. You can configure default task parameters and instructions.

Connect Scale Ai to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Scale Ai in Metorial. In your Metorial portal, enable the Scale Ai MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Scale Ai tools.

Run Scale Ai through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Scale Ai and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Scale Ai tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Scale Ai

Notion

Create, read, update, and archive pages and databases in a Notion workspace. Manage blocks (paragraphs, lists, headings, embeds, etc.) within pages. Query databases with filters and sorts across rich property types including text, numbers, dates, selects, relations, and formulas. Search across pages and databases by title. Add and read comments on pages and blocks. Upload files to pages. Manage workspace users and retrieve user profiles.

Google Sheets

Create, read, and update spreadsheets and their cell data. Read and write values to individual cells, ranges, or multiple ranges using A1 notation or named ranges. Apply cell formatting including text styles, backgrounds, borders, number formats, and conditional formatting. Manage sheets (tabs) within a spreadsheet—add, delete, copy, rename, and reorder them. Create and manage embedded charts, pivot tables, filter views, data validation rules, protected ranges, named ranges, and merged cells. Perform batch operations to apply multiple updates atomically.

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Microsoft Outlook

Send, read, reply to, forward, and manage email messages in user mailboxes. Organize messages into folders, apply categories, flags, and importance levels. Manage file and item attachments. Create, update, delete, and respond to calendar events and meetings. Find available meeting times, manage attendees, handle recurrence, and work with shared or delegated calendars. Create, read, update, and delete contacts, organize them into contact folders, and manage contact photos. Manage tasks and task lists via Microsoft To Do, including due dates, reminders, recurrence, and checklist items. Support for Focused Inbox, @-mentions, mail tips, send-on-behalf, and send-as capabilities.

Technical notes for Scale Ai

Create and manage data labeling and annotation projects for AI/ML training data. Submit tasks for image annotation (bounding boxes, polygons, segmentation), video annotation with tracking, 3D LiDAR/sensor fusion annotation, document transcription, and text annotation. Manage projects, batches, and taxonomies/ontologies for structured labeling workflows. Support pre-labeling with model-generated hypotheses, quality auditing, evaluation tasks, and team management for annotation teams. Receive task and batch completion notifications via webhooks.

Frequently asked questions

Common questions about connecting Scale Ai to AI agents with Metorial.

  1. How many tools does the Scale Ai MCP server have?
    The Scale Ai MCP server exposes 17 tools, including Update Task, Get Batch, Create Batch. Each one is governed and traced through Metorial.
  2. Scale Ai exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Scale Ai MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Scale Ai and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Scale Ai MCP server yourself or use the hosted gateway.

Connect Scale Ai to production AI agents

See how Metorial gives your team governed access to Scale Ai, with tracing and security controls built in.