Skip to main content

Prerequisites

  • MCP Toolbox installed
  • A tools.yaml configuration file for your toolbox setup

Installation

First, check the current version:
Choose your preferred installation method:

Enable Telemetry

Set this environment variable before running the server. Use whichever mechanism your environment provides, such as a shell configuration, .env file, container configuration, or deployment-platform settings:
Then run your MCP Toolbox with telemetry enabled and point it to Agnost AI:
Replace <your-agnost-org-id> with the organization ID from your Agnost AI dashboard.

Docker Usage

If using Docker:

That’s It!

Your MCP Toolbox is now sending telemetry data to Agnost AI. Visit your Agnost AI dashboard to:
  • Monitor tool invocations in real-time
  • Track performance metrics and response times
  • Analyze usage patterns and optimization opportunities
  • Set up alerts for performance issues

Verify

Call one Toolbox tool, then open Events and Tool calls in Agnost AI. You should see the tool name, latency, success/failure, and exported metadata.

Troubleshooting

  • Confirm OTEL_EXPORTER_OTLP_HEADERS contains X-Agnost-Org-ID=<your-agnost-org-id>.
  • Confirm Toolbox is started with --telemetry-otlp="otel.agnost.ai".
  • If running Docker, confirm the env var is passed into the container.

Need Help?

MCP Toolbox Support Resources

Next steps

  • Tool calls: analyze Toolbox usage, outcomes, and latency.
  • Events: inspect the exported OpenTelemetry records.
  • Alerts: monitor important tool conditions.