MCP Server

Prev Next

Pigment offers Model Context Protocol (MCP) solutions that developers can use to access Pigment features securely through AI systems such as ChatGPT.

What is MCP?

MCP is an open standard that allows AI systems to connect to external tools and data sources in a controlled, secure, and structured way.

By exposing Pigment capabilities via MCP, you enable AI systems to query data and retrieve insights directly from Pigment—all while respecting user permissions and Workspace security policies.

Available Pigment tools

Tool

Description

Sample Prompt

Get Applications

Returns the list of Applications in a given Workspace. Only Applications the authenticated user has access to are shown.

“List all my Pigment Applications.”

Query Data

Returns data requested by the user. Available only for Metrics where AI Search is enabled. Learn more.

“Show me Revenue.”
“Show me Revenue for EMEA and AMER regions.”

“Show me Sales for top 10 products by Year.”

How to connect to the Pigment MCP Server

Before you begin

⚠️ Important

You need the Role and access rights of Security Administrator, Workspace Administrator or Primary Owner to set up MCP.

Your Workspace needs to have AI activated. For this, submit a Support ticket following the guidance on our Pigment AI page, choosing “Data, Documentation Assistant and MCP Server” under AI Feature request.

Ensure "AI Search" is activated on key Metrics which you want MCP to read from.

1. In Pigment

  1. From November 26, request activation by submitting a Support ticket, selecting MCP Server.

  2. Once you have been notified in the ticket that MCP has been activated, go to your Workspace and select Settings from the sidebar.

  3. Select Integrations from the sidebar then the MCP tab in the main pane.

  4. Toggle on MCP (Model Context Protocol).

A unique MCP Endpoint URL is generated, which you will need to connect a third-party AI system to Pigment. If you plan to connect multiple Workspaces, each must have its own MCP Endpoint URL and connector.

2. In your AI system

Use the MCP Endpoint URL to connect third-party AI systems to Pigment tools. We currently support ChatGPT—support for other AI systems is in development.

ChatGPT

Documentation

Create connector

  1. You need Developer Mode enabled.

  2. Go to Settings and select Apps & Connectors.

  3. Select Add a new connector.

  4. Name your connector (e.g. “Pigment”).

  5. Paste your Pigment MCP Server URL and click Add.

Use connector

  1. Start a new chat.

  2. Click Add files & more then More and select your custom Pigment connector.

  3. Go through the authentication workflow using your Pigment credentials.

  4. Once connected, your Pigment tools appear in the list of available connectors.

  5. Begin your conversation. Pigment tools can now be invoked directly in chat.

Claude (coming soon)

Documentation

Create connector

  1. You need Owner privileges.

  2. Go to Admin settings and select the Connectors tab.

  3. Select Add a custom connector.

  4. Name your connector.

  5. Paste your Pigment MCP Server URL and select Add.

Use connector

  1. Go to Settings and select the Connectors tab

  2. Click on Connect and go through the authentication workflow using your Pigment credentials.

  3. Start a new chat and select Search & Tools to verify that your Pigment connector is active and tools are available.

  4. Begin your conversation. Pigment tools can now be invoked directly in chat.

Permissions and access rights

When a user accesses Pigment via an MCP connector, they must authenticate with their Pigment account.

All existing Pigment permissions and access rights apply:

  • Users can only access Applications, Metrics, or data they already have access to in Pigment.

  • No additional access is granted through MCP.

Troubleshooting

If you encounter issues while connecting:

  • Connection fails: verify that your MCP URL is active and the MCP Server is enabled in your Pigment Workspace.

  • Authentication errors: make sure you have the correct role and are using valid Pigment credentials.

  • Tools not visible: confirm that AI Search is enabled for the Metrics you want to query.

  • Multiple Workspaces: check that you’re using the correct MCP URL for the Workspace you’re trying to access.