An astronaut overseeing a futuristic data hub

Connect Coalesce 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 and monitor data transformations directly from your chat interface.

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.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

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.

A futuristic MCP client docking bay
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 · 8 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through Coalesce.

  1. 01

    Trigger job

    Starts a specific job within a chosen environment.

  2. 02

    Trigger run

    Initiates a new run for an environment and can target a specific job.

  3. 03

    Get environment

    Fetches detailed configuration data for a single environment.

  4. 04

    Get run status

    Checks the current progress and status of a run you just started.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through Coalesce.

  1. 05

    List environments

    Returns a list of all environments in your Coalesce organization.

  2. 06

    List jobs

    Provides a list of jobs, with the option to filter by environment.

  3. 07

    Get job details

    Retrieves specific metadata and details about a single job.

  4. 08

    List nodes

    Gets metadata regarding the transformation nodes in an environment.

Real work

What teams actually run

01

Rapid Pipeline Retries

After a failure, you tell your agent to trigger a specific job to try the run again.

02

Status Checks

You ask your agent for the progress of a production run while you work in another capability.

03

Environment Audits

You use the agent to list all environments and verify their current configurations.

04

Debugging Failed Jobs

You ask for job details and node metadata to identify why a transformation failed.

Automate a task

Put Coalesce 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

Coalesce 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 Coalesce 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

885ms average. Fast in production.

Coalesce is checked daily against the live service.

Daily averagePeak 1025ms
Oct 3Today
Fastest day
669ms
Slowest day
1025ms
14-day trend
Stable-2%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 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 Coalesce, so you can see the experience inside your AI.

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

Coalesce Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_Cc4llz27o6QgNOF3cmyYyEYcNpp6loEG8VfVdFq3/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Coalesce capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "coalesce-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Cc4llz27o6QgNOF3cmyYyEYcNpp6loEG8VfVdFq3/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 Coalesce in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Coalesce owners hand off.

This MCP is built for technical users managing Snowflake data transformations through Coalesce.

  • 01

    Data Engineers

    They use the agent to trigger and monitor pipeline runs without opening the Coalesce UI.

  • 02

    Analytics Engineers

    They use the agent to check job statuses and debug failed transformations via chat.

  • 03

    Data Team Leads

    They use the agent to get quick health checks on environments and recent job results.

FAQ

Questions Coalesce owners ask.

  • 01

    How do I connect this MCP to my Coalesce account?

    You need to provide your API Token, which you can find in your Coalesce Organization Settings under API Tokens.

  • 02

    Can I trigger specific parts of a pipeline?

    Yes, you can trigger specific jobs or use node selectors to target specific parts of your transformations.

  • 03

    Which AI clients can use this MCP?

    This MCP works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 04

    Does this MCP work with Snowflake?

    Yes, this MCP is specifically designed for Coalesce, which is a transformation platform built for Snowflake.

  • 05

    Can I see why a job failed?

    Yes, your agent can retrieve job details and check the status of runs to help you identify issues.

  • 06

    How do I get my Coalesce API token?

    In the Coalesce UI, go to Organization Settings > API Tokens and generate a new token. Copy it and paste it below.

  • 07

    Does this work with Snowflake?

    Yes. Coalesce is built specifically for Snowflake. The API triggers jobs that run directly on your Snowflake instance.

  • 08

    What is a Node Selector?

    A Node Selector lets you filter which transformation nodes to include in a run, based on name, type, or tags.

Connect Coalesce to Claude, Cursor, ChatGPT & more