Geckoboard’s MCP connector gives compatible AI tools the ability to access data from the services you've got connected to Geckoboard.
Once connected, you can ask your AI assistant to help investigate changes in a metric, look for interesting patterns and trends, run calculations across data sources, and more. More broadly, the MCP enables you to build AI agents that can operate based on real-time operational metrics from your most important tools.
Currently the MCP supports the following integrations: HubSpot, Zendesk, Aircall, Pipedrive, Google Analytics, Google Ads, Google Search Console, Facebook, Facebook Ads, Instagram, LinkedIn, LinkedIn Ads, YouTube.
Support for more integrations is planned - let us know what you'd like to see added next.
Connect Geckoboard to Claude
Open Claude (desktop or web)
Go to Customize > Connectors.
Click the + button next to Connectors.
Select Add custom connector.
Enter the following details:
Name: Geckoboard
URL:
https://gateway.geckoboard.com/mcp
Click Add.
Click Connect and follow the on-screen authorization flow.
Start a new chat.
Connect Geckoboard to ChatGPT
Full MCP support in ChatGPT is currently in beta, and not available on all plans.
Enable Developer Mode in ChatGPT on the web.
Go to Settings > Apps.
Click Create app next to Advanced settings.
Enter the following details:
Name: Geckoboard
URL:
https://gateway.geckoboard.com/mcp
Click the checkbox to accept the risk of using Developer mode.
Click Create.
Click Sign in with Geckoboard and follow the authorization flow.
Start a new chat.
Connect Geckoboard to other AI tools
The exact setup flow varies between tools, but the usual steps are:
Open your AI tool's settings.
Find the option to add a new custom MCP server.
Enter the Geckoboard MCP URL.
Choose HTTP or Streamable HTTP as the transport.
Authenticate with Geckoboard when prompted.
Save the connection and enable it in your AI tool.