Using Adverity MCP (Beta)

Using Adverity MCP (Beta)#

This guide explains how to connect to Adverity from your AI tools using MCP.

Note

This feature is in beta stage.

Introduction#

What is Adverity MCP?

Adverity Model Context Protocol (MCP) connects your AI assistant to Adverity, allowing you to monitor data pipelines, check authorization status, and download data extracts using natural language. Instead of navigating the Adverity interface, you can simply ask your AI tool questions like “Show me all failed fetches from the last 24 hours” or “Download my latest Google Ads data”.

What are the benefits of using Adverity MCP?

With Adverity MCP you can:

Monitor your data pipelines without leaving your AI assistant.
Get instant answers about datastream status, fetch history, and authorization health.
Download data extracts on demand through simple prompts.
Troubleshoot failed jobs by asking questions in plain language.

What can I do with Adverity MCP?

With Adverity MCP you can monitor, configure, and control your data pipelines:

Create and manage datastreams, their configurations, and current status.
Create and manage authorizations, check expiry dates and connection health.
Trigger fetches, review job history, and troubleshoot errors.
Download CSV data extracts from successful datastream executions.
Explore your workspace structure.

Is my data secure?

Adverity MCP uses your existing MAPI key for authentication, so the AI assistant only has access to data permitted by your key’s permissions. All communication happens through secure, authenticated connections.

Prerequisites#

Before using Adverity MCP, ensure you have all of the following:

Adverity Account

An active Adverity account with Management API (MAPI) access enabled.

Adverity instance URL

Your dedicated environment address, such as https://yourcompany.adverity.com.

Adverity MAPI key

A valid API key generated from your Adverity instance. The key permissions determine what actions AI can perform. For more information, see Generating an API key in Adverity.

Compatible MCP client

An AI tool account that supports MCP connections:

Claude: Requires a Claude Pro or higher plan that supports custom connectors.
ChatGPT: Requires a Business or Enterprise plan. Note that initial setup may require workspace administrator privileges to enable developer mode for custom connectors.

Connecting AI tools#

Connecting to Claude#

To connect Adverity to Claude with MCP, follow these steps:

Open Settings in Claude.ai and navigate to Connectors.
Click Add custom connector.
Configure the connection:

Name
Enter the name for your Adverity connection.

Remote MCP server URL
Enter the URL of the Adverity MCP server: https://mcp.eu.adverity.com/mcp.
Click Add. You will be redirected to the Adverity MCP server sign in page.
Enter your Instance URL and MAPI key to authenticate the connection.
Click Connect Adverity to MCP.

Your Adverity instance is now connected to Claude. Start your first conversation.

Managing Claude tool permissions#

In Claude, you can control how the assistant executes specific MCP tools:

Always allow (recommended): Claude can use the tool without user confirmation, which allows it to work efficiently without interrupting for permission on every query.
Needs approval: Claude must ask for permission each time, providing more control but slower execution.
Blocked: Prevents Claude from using specific tools entirely.

Connecting to ChatGPT#

For ChatGPT, an administrator needs to create the connector first, then individual users can link their accounts.

Setting up the connector (administrator)#

To set up the Adverity MCP connector in your ChatGPT workspace, follow these steps:

In ChatGPT, click your workspace name in the bottom-left corner and select Workspace settings.
Go to the Connectors tab.
Click Create.
A pop-up will appear warning about developer mode. Click Enable developer mode.
Configure the connection:

Name
Enter the name for your Adverity connection.

MCP Server URL
Enter the URL of the Adverity MCP server: https://mcp.eu.adverity.com/mcp.

Authentication
Leave this setting empty.
Check the box I understand and want to continue.
Click Create. You will be redirected to Adverity to authenticate with your MAPI key.
After authenticating, you will be redirected back to the ChatGPT Connectors settings page.
Your new connector will be listed under Drafts. Click Publish.
Acknowledge the potential risks in the pop-up.
Click Publish again.

The Adverity MCP connection is now active and available for all users in your workspace.

Connecting your personal account (user)#

Once your administrator has set up the connector, follow these steps to link your personal account:

In ChatGPT, click your name in the bottom-left corner and select Settings.
Go to the Apps & Connectors tab.
Click Adverity in the list of available connectors.
Click Connect.
A pop-up will appear. Click Continue to Adverity.
You will be redirected to the Adverity sign in page. Enter your Instance URL and MAPI key to authenticate the connection.
After a successful sign in, you will be redirected back to your ChatGPT settings. The button will now say Disconnect, confirming the connection is active.

Your Adverity instance is now connected to ChatGPT. Start your first conversation.

Connecting to other tools#

MCP is designed for broader agentic workflows beyond chat interfaces. You can integrate Adverity MCP with automation platforms and custom applications using the MCP server URL: https://mcp.eu.adverity.com/mcp.

n8n and Make: Build automated workflows where an AI agent checks if datastreams are successful before triggering the next step in a marketing report.
Custom clients: Build your own MCP clients to allow different internal AI agents to collaborate using Adverity’s harmonized data as a central hub.

Available MCP tools and use cases#

The MCP server provides five specialized tools organized by domain:

manage_datastream: Lists, creates, and configures datastreams. View status, enable or disable pipelines, explore available connector types and their field options. Core tool for pipeline management and troubleshooting.
manage_authorization: Manages authorizations for connected data sources (Google Ads, Facebook Ads, LinkedIn Ads, etc.). Create new connections, monitor expiry dates, handle OAuth flows, and refresh metadata from external APIs. Essential for preventing pipeline failures.
manage_fetch: Controls data collection jobs and schedules. Trigger fetches on demand or for specific date ranges, monitor job status, stop running jobs, and configure fetch schedules. Critical for troubleshooting and managing data collection.
manage_extract: Lists and downloads data extracts as CSV files, either the latest data or from specific dates.
manage_workspace: Shows workspace structure and which datastreams belong where. Useful for multi-workspace environments.

Example prompts#

To get the most relevant results, be specific in your prompts by including timeframes, workspace names, or datastream names. With Adverity MCP, you unlock the following use cases directly from your AI tool:

Monitoring datastreams

Show me all my datastreams.
List all datastreams in the Marketing workspace.
Which datastreams are currently disabled?

Checking authorizations

Which authorizations are expiring soon?
Show me all expired authorizations within the last 24 hours.
What is the status of my Google Ads authorization?

Reviewing fetch history

What were the results of recent fetches for the Pinterest datastream?
Show me all failed fetches within the last 24 hours.
Why did my Facebook Ads fetch fail?

Downloading data

Download my latest Google Ads data.
Get the most recent data extract for the LinkedIn Ads datastream.

Exploring workspaces

What workspaces do I have access to?
Which datastreams belong to the Production workspace?