How to Use the Coalesce MCP in Mastra AI

Q: How do I register Coalesce tools in a Mastra AI agent?

Initialize the client using @mastra/mcp with your Vinkius MCP endpoint URL. Then, call listTools() on the client and spread those tools directly into your agent configuration.

Q: Does Mastra AI support human-in-the-loop for Coalesce transformations?

Absolutely, you can use the framework's requireToolApproval flag on sensitive operations like triggerjob. The workflow pauses and waits for manual verification before sending the execution command to your pipeline.

Build Mastra AI workflows that automatically trigger, monitor, and recover Coalesce Snowflake jobs when pipeline errors occur.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coalesce MCP to Mastra AI

Create your Vinkius account to connect Coalesce to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Coalesce with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated pipeline recovery in Mastra AI workflows

With the `trigger_run` and `get_run_status` tools, your Mastra AI workflows recover from failed data transformations automatically. When a run fails, the framework catches the error and executes a retry loop with exponential backoff. You define the recovery logic in plain TypeScript. The agent monitors the run until it succeeds, preventing broken pipelines from stalling your downstream analytics.

Conditional branching based on environment states

Running the `list_environments` and `get_environment` tools gives your Mastra AI agents the context they need to make execution path decisions. Before triggering any heavy transformations, the agent checks which target environment is active and healthy. If the staging environment is offline, the workflow branches to notify your engineering channel. This prevents useless API calls and keeps your production data warehouse clean.

Safe job execution via Coalesce MCP Server approvals

Integrating the `trigger_job` and `list_jobs` tools with Mastra AI's manual approval gates keeps critical production changes safe. Your agent executes these tasks via the MCP Server, drafting the job parameters and pausing execution until a human clicks approve. This setup ensures no one accidentally wipes a production table. You get the speed of an autonomous agent with the safety of manual oversight.

Setup guide

Set up Coalesce MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Coalesce tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "coalesce-mcp-client",
  servers: {
    "coalesce-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Coalesce Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Coalesce tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Coalesce transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Coalesce. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Coalesce now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Coalesce MCP in Mastra AI

Initialize the client using `@mastra/mcp` with your Vinkius MCP endpoint URL. Then, call `listTools()` on the client and spread those tools directly into your agent configuration.

Yes, Mastra's built-in workflow engine handles this natively. You can configure automatic retries for the `trigger_run` tool, letting the agent back off and try again if your Snowflake warehouse is temporarily overloaded.

Absolutely, you can use the framework's `requireToolApproval` flag on sensitive operations like `trigger_job`. The workflow pauses and waits for manual verification before sending the execution command to your pipeline.

The system automatically detects and uses Streamable HTTP or Server-Sent Events (SSE). This ensures low-latency communication between your Mastra workflows and the Coalesce API.

Your pipeline schemas and job histories are protected by Vinkius's isolated V8 sandboxes. This secure MCP setup ensures all API keys are encrypted at rest, and execution environments are torn down instantly after your workflow completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript