Skip to content

Artificial Intelligence

Supervisely MCP connector

The Supervisely connector brings your annotation objects, tags, and labeling agents into Claude, ChatGPT, Cursor, and any other MCP client, so your team can review, tag, merge, and clean up labels while every action runs inside their own Supervisely access.

  • How it connects. Connects with an API key. The credential goes into a vault nobody reads back.

  • One address. https://api.elaichi.ai/mcp, the same for every user.

  • Their own access. An agent never gets more than the person it acts for.

How to connect

How to connect Supervisely to Claude, ChatGPT or Cursor

Two steps, about a minute.

1

In Elaichi

Connect Supervisely once

  1. Open Connections, choose Add connection, and pick Supervisely.

  2. Optionally set Share with to give a team access, then press Connect.

  3. Paste a Supervisely API key. One person generates a token in Supervisely and pastes it once. Everyone else works through Share with, and never sees it.

The credential is vaulted. Nobody reads it back, not even the AI.

Add connection

Choose a connector.

supervisely
Supervisely
AirOps
Algolia
Botpress
Chatvolt
Cohere
2

In your AI client

Point it at one endpoint

Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.

Connect Supervisely to Claude

  1. 1

    Open Customize, then Connectors.

  2. 2

    Press Add.

  3. 3

    Name it, paste the MCP server URL, then Continue.

    https://api.elaichi.ai/mcp
  4. 4

    Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

Connect Supervisely to ChatGPT

  1. 1

    Open Plugins, then press the + button.

  2. 2

    Name it and paste the endpoint into Server URL.

    https://api.elaichi.ai/mcp
  3. 3

    Leave Authentication on OAuth, then tick the risk acknowledgement.

  4. 4

    Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

Connect Supervisely to Cursor

  1. 1

    Open ~/.cursor/mcp.json.

  2. 2

    Add the endpoint under mcpServers.

    https://api.elaichi.ai/mcp
  3. 3

    Reload Cursor, then sign in and approve.

~/.cursor/mcp.json

{
  "mcpServers": {
    "elaichi": {
      "url": "https://api.elaichi.ai/mcp"
    }
  }
}

Set up per machine, so repeat it on each computer you work from.

Connect Supervisely to any MCP client

  1. 1

    Add the endpoint as a remote MCP server.

    https://api.elaichi.ai/mcp
  2. 2

    Sign in and approve.

{
  "mcpServers": {
    "elaichi": {
      "url": "https://api.elaichi.ai/mcp"
    }
  }
}

The Elaichi Agent already has these tools, with nothing to set up.

Use cases

What teams do with Supervisely through Elaichi

Every one of these runs inside the access the person already has, and lands in the same audit log.

  • Annotation

    Tag a batch of objects in one go

    Ask for every object in a set to get a class or attribute tag applied at once, instead of clicking through them one by one.

  • Annotation

    Merge or split labels after review

    Ask to merge duplicate objects that were drawn twice, or split an object that should have been two, without opening the editor.

  • Machine learning

    Check which agents are online

    Ask which Supervisely agents are available and ready before kicking off a training or inference job.

  • Machine learning

    Upgrade agents across the fleet

    Ask to upgrade the agents that are behind and set their status, so nothing runs on an outdated version.

  • Quality review

    Find objects with missing tag values

    Ask for the tag values on a group of annotation objects and spot the ones that were left blank or set inconsistently.

  • Operations

    Clean out bad labels in bulk

    Ask to remove a list of annotation objects that failed review, once the removal has been approved and the objects are confirmed.

Try asking

  • “List Supervisely agents that are available right now.”
  • “Which projects gained the most annotation objects this week?”
  • “Add the review tag to yesterday's labeled objects.”

See all 455 Supervisely tools below

AI tools

Supervisely tools for your AI agents

455 tools are ready to call through Elaichi's MCP endpoint the moment you connect Supervisely, governed by the same roles, restrictions, and audit log as everything else in Elaichi.

See it in Elaichi

What connecting Supervisely gets you

6 screens from the product, each doing one job for your Supervisely account.

The agent

Ask about agents and annotations, get answers.

Plain language questions run against live Supervisely agents, projects and annotation tags.

  • agents
  • projects
  • annotation objects
  • tags

Ask Elaichi to work across your apps.

List Supervisely agents that are available right now.

Which projects gained the most annotation objects this week?

Add the review tag to yesterday's labeled objects.

Also runs in Claude, ChatGPT or Cursor

MCP clients

Claude, ChatGPT and Cursor share one endpoint.

Connect any MCP client to Supervisely over OAuth, no SDK, no shared key.

ElaichiMCP clients
Claude ChatGPT Cursor

Copy the endpoint

https://api.elaichi.ai/mcp
Client Connected by Status Last used
Claude
E

Emma Laurent

• Connected 4 minutes ago
Cursor
S

Sofia Ricci

• Connected 2 hours ago
ChatGPT
C

Clara Nowak

• Connected Yesterday

Tool catalog

455 Supervisely tools ready without custom code.

Browse tool names, resources and methods across agents, projects, annotations and tags.

  • Create a Supervisely agents net set status
  • Supervisely agents exists
  • Supervisely agents available
  • List all Supervisely agents
ElaichiTools
Tool Action Description
Create a Supervisely agents net set status Create Update the network status of a Supervisely agent by recording its last-seen timestamp. Returns an opaque success object. Required: token, lastSeenAt.
Supervisely agents exists Action Check whether a Supervisely agent exists by its token. Returns: agent, 5XX. Required: token.
Supervisely agents available Action List available Supervisely agents for a team, optionally filtered by capability type, GPU requirements, and environment variables. Returns: id, name, token, userId, createdAt, updatedAt, capabilities. Required: teamId.
List all Supervisely agents List List all Supervisely agents in a team with sorting and filtering options. Returns: id, name, token, userId, createdAt, updatedAt, capabilities. Required: teamId.
Supervisely agents upgrade Action Queue an upgrade task for a Supervisely agent by token. The agent recreates its container on the latest released version and disconnects briefly. Returns a success response. Required: token.

Toolboxes

Every team gets its own Supervisely toolbox.

Curate one toolbox per team so labeling, ML and ops see different tools.

  • Labeling
  • ML engineering
  • Data operations
  • Quality review
ElaichiToolboxes
Name Source template Tools Created

Labeling toolbox

Supervisely · annotation objects and tags

Supervisely starter 18 Mar 4, 2026

ML engineering toolbox

Supervisely · agents and training jobs

9 Mar 2, 2026

Data operations toolbox

Supervisely · datasets and imports

24 Feb 27, 2026

Quality review toolbox

Supervisely · labeling jobs and reviews

Supervisely starter 6 Feb 19, 2026

Research toolbox

Supervisely · projects and model runs

31 Jan 30, 2026

Platform toolbox

Supervisely · agent status and storage

12 Jan 22, 2026

Shared connections

Teammates use Supervisely without seeing a credential.

The connections table shows who connected each account and how widely it is shared.

  • Labeling EMEA
  • ML engineering
  • Data operations
  • Quality review
ElaichiConnections
Connection Scope Status Access
SU

Supervisely (Labeling EMEA)

Connected by Emma Laurent

Personal • Active 1 team · 6 members
SU

Supervisely (ML engineering)

Connected by James Whitfield

Organization • Active 3 teams · 24 members
SU

Supervisely (Data operations)

Connected by Sofia Ricci

Organization • Active 2 teams · 11 members
SU

Supervisely (Quality review)

Connected by Daniel Ortega

Personal • Needs re-auth 1 team · 3 members
SU

Supervisely (Research)

Connected by Clara Nowak

Personal • Active Not shared
SU

Supervisely (Platform)

Connected by Michael Brennan

Personal • Active 2 teams · 9 members

Audit log

Every Supervisely call is written down.

When, who, what happened, type and resource, in an append only log.

  • When
  • Who
  • What happened
  • Type
ElaichiAudit log
When Who What happened Type

2 minutes ago

Mar 6, 2026, 3:10 PM

E

Emma Laurent

[email protected]

Restriction Created Access

8 minutes ago

Mar 6, 2026, 3:04 PM

J

James Whitfield

[email protected]

Restriction Updated Access

14 minutes ago

Mar 6, 2026, 2:58 PM

S

Sofia Ricci

[email protected]

Role Assigned Access

20 minutes ago

Mar 6, 2026, 2:52 PM

D

Daniel Ortega

[email protected]

Supervisely Users Updated MCP

26 minutes ago

Mar 6, 2026, 2:46 PM

C

Clara Nowak

[email protected]

Supervisely Agents Created MCP

32 minutes ago

Mar 6, 2026, 2:40 PM

M

Michael Brennan

[email protected]

Supervisely Agents List Toolbox

Launching soon

From answering questions to doing the work

A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.

Automations

A schedule fires, a digest ships.

Six steps fetch Supervisely jobs, group them, draft a digest, await approval, post back.

Supervisely digest

Run 418 · started 2 minutes ago · on behalf of Emma Laurent

  1. Schedule

    Every weekday at 08:00

    0.2s
  2. Fetch agents

    Supervisely

    1.4s
  3. Group by owner

    Transform

    0.1s
  4. Draft the digest

    Agent step

    Ran with 4 tools, returned a structured summary

    6.2s
  5. Approve the digest

    Needs approval

    Assigned to Michael Brennan

    Approve
  6. Post the digest

    Supervisely

    Queued

Collections and dashboards

Supervisely numbers arrive before anyone asks.

Four metrics, 14 days of created annotations and a team breakdown, refreshed on schedule.

Supervisely health

Refreshed 4 minutes ago · every 15 minutes · from the agents collection

Live

Agents

1,284 ↓ 12%

Projects

96 ↓ 8%

Needs attention

3 ↑ 2

Updated this week

412 ↑ 9%

Agents created

Last 14 days

By team

Share of activity

Labeling EMEA 34%

ML engineering 27%

Data operations 21%

Quality review 18%

FAQ

Frequently asked questions

How do I connect Supervisely to Claude?

Two steps. First, connect Supervisely in Elaichi, which asks you to paste your Supervisely API key; there is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Sign in with your Elaichi account and Supervisely is ready to use in Claude.

Does Supervisely work with ChatGPT and Cursor as well as Claude?

Yes. Once Supervisely is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Supervisely once and use it from every client.

What can an AI agent actually do with my Supervisely data?

With Supervisely connected, an agent can list your annotation objects, look up a single object, add tags to one object or to a whole batch, merge, split, or swap objects, and update or remove objects in bulk. It can also list your Supervisely agents, check which are available, create new ones, upgrade them, and change their status. Because Supervisely offers hundreds of actions, short concrete asks like "tag these objects as vehicle" work better than long sentences.

Does connecting Supervisely give the AI access to my whole workspace?

No. Every call to Supervisely runs inside the access of the person who signed in, so an agent sees the same teams, projects, and annotation objects that person can already reach in Supervisely. Elaichi can narrow that access further with restrictions, and it can never widen it beyond what the person already has.

Can my team share one Supervisely connection?

Yes. One person connects Supervisely in Elaichi and shares the connection with a team, and nobody else on the team ever handles the API key. Each person still signs in to Elaichi as themselves, so the audit log records who tagged, merged, or removed each annotation object.

Can I stop an agent from deleting or changing things in Supervisely?

Yes. Restrictions in Elaichi work per action, so you can allow reading annotation objects and adding tags while blocking bulk removal or object updates in Supervisely. A blocked action is never advertised to the AI client at all, so no prompt can reach it.

What happens to a Supervisely connection when someone leaves?

Offboarding a person in Elaichi ends their access to Supervisely through every client at once. A shared Supervisely connection keeps working for everyone else on the team. If you want to remove Supervisely entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client.

Put Supervisely in front of your team

Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.