# Integrate.io MCP

> Integrate.io (ETL & Data Integration) lets you manage complex data pipelines and ETL jobs using natural conversation. List all your active packages, track job runs for failures, audit every connection, or check account credit limits—all without leaving your AI client.

## Overview
- **Category:** brain-trust
- **Price:** Free
- **Tags:** etl-pipelines, data-integration, pipeline-monitoring, data-transformation, data-warehouse, job-scheduling

## Description

You can take full control of your automated data workflows through this MCP. Instead of logging into a web dashboard to manage data pipelines, you talk to your agent and get the answers instantly. Need to know what data moved last night? Your agent runs `list_jobs` and tells you if the sync succeeded or failed. Want to verify that the 'Stripe' connection is still pointing to the right database? You simply ask it to list connections, checking credentials in seconds. It also lets you check account limits with a simple call to get your overall status, helping you manage your budget while running complex data transformations. This MCP connects deep infrastructure actions—like listing all data transformations or retrieving specific pipeline details—directly into your workflow via Vinkius. You use this for everything from checking job history to inspecting schemas.

## Tools

### list_pipelines
Shows you a list of every data pipeline currently configured in your Integrate.io account.

### get_pipeline
Pulls all the technical details, schemas, and variables for one specific pipeline using its ID.

### list_jobs
Retrieves a log of both successful and failed jobs to see when your data ran last.

### list_connections
Provides an inventory of all database credentials and API connections you've set up.

### list_transformations
Lists every data transformation rule in place, allowing you to audit how data is mapped from source to target.

### get_account
Checks your overall Integrate.io account status, including limits and remaining processing credits.

## Prompt Examples

**Prompt:** 
```
List all my data pipelines in Integrate.io
```

**Response:** 
```
I've found 5 active pipelines: 'Shopify to Snowflake', 'Stripe Data Sync', 'Customer CRM Export', 'Marketing Analytics', and 'Inventory Hub'. Which one would you like to see the details or run history for?
```

**Prompt:** 
```
Show me the status of the last 3 jobs
```

**Response:** 
```
Retrieving job history… The last 3 jobs were: 1) 'Shopify Sync' (Success, 12 min ago), 2) 'CRM Export' (Failed, 1 hour ago - connection timeout), 3) 'Stripe Sync' (Success, 3 hours ago). Would you like to inspect the error for the failed job?
```

**Prompt:** 
```
What data sources are currently connected to my account?
```

**Response:** 
```
I've identified 4 connected data sources: 'Production PostgreSQL', 'Cloud Snowflake DW', 'Stripe API', and 'HubSpot CRM'. All connections are active and ready for pipeline use. Would you like to see the transformation models mapped to 'Snowflake'?
```

## Capabilities

### List active pipelines
View every scheduled data package in the Integrate.io account with one command.

### Get specific pipeline details
Retrieve a deep dive into the structure, nodes, and variables of any single data pipeline by its ID.

### Monitor job history and status
Track the success or failure status of past and current automated jobs to confirm data warehouse updates ran correctly.

### Audit data connections
Enumerate all linked database credentials and API sources used across your entire data infrastructure.

### Inspect transformation logic
List and review the detailed mapping rules for every data transformation you've set up in your account.

### Check account limits
Get real-time status on your workspace credits, remaining usage, and overall account metrics.

## Use Cases

### The Data Engineer needs a failure root cause.
A nightly job fails, leaving the warehouse empty. Instead of manually clicking through logs and dashboards for hours, the engineer asks the agent to run `list_jobs` then uses `get_pipeline` on that specific pipeline ID. The agent immediately pulls up the schema details and shows where the connection variable is failing.

### The Analytics Lead must prove data lineage.
A VP asks, 'How did we get this revenue number?' The lead doesn't know the exact path. They ask the agent to run `list_transformations` and then use `list_connections`. This quickly maps out every source and rule used to calculate the final metric.

### The Operations Analyst is managing cost overruns.
Billing seems high. The analyst asks the agent for the account status using `get_account`. The response shows low remaining credits, prompting them to review all active sources by running `list_connections` and find an unused API key.

## Benefits

- Stop jumping between tabs. Instead of logging into the dashboard just to check if your nightly 'Stripe Sync' succeeded, ask your agent to run `list_jobs` and get the status immediately.
- Audit data integrity instantly. Need to confirm which sources feed a report? Use `list_connections` to inventory every database and API source before running any major analysis.
- Control your budget in real-time. Instead of guessing where your credits are going, use `get_account` to see exactly how many processing units you have left for the month.
- Understand complex data flows quickly. When a pipeline fails, don't just get an error code; ask for details using `get_pipeline` to see which specific node or variable caused the issue.
- Verify your setup before deployment. Use `list_transformations` to inspect every mapping logic and ensure the source data is being correctly converted into the target schema.

## How It Works

The bottom line is you control complex data infrastructure directly through chat, eliminating dashboard hopping.

1. First, subscribe to this MCP and provide your Integrate.io API Key.
2. Next, connect the credentials from any compatible AI client (like Cursor or Claude).
3. You can then use natural conversation prompts to run commands like listing pipelines or checking job statuses.

## Frequently Asked Questions

**How do I check if a specific ETL job ran successfully using Integrate.io (ETL & Data Integration)?**
You use the `list_jobs` tool to see the history of runs. This shows you success status, failure times, and which pipelines were involved in the run.

**Can I list all my data sources with Integrate.io (ETL & Data Integration)?**
Yes, running `list_connections` pulls an inventory of every database and API connection you have set up for your pipelines.

**How do I see the details of a specific data pipeline?**
Use the `get_pipeline` tool. You must provide the unique ID, and the agent will return all technical specifics like schemas and variables associated with that package.

**What is the best way to check my remaining Integrate.io credits?**
The `get_account` tool provides a real-time view of your account status, including current usage and remaining processing credits so you don't hit a spending limit.

**Does Integrate.io (ETL & Data Integration) help me audit data transformations?**
Yes, running `list_transformations` shows you every mapping rule established in your account. This is crucial for verifying data quality logic.