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 your Agnost organization ID as an environment variable before running the server:
MCP Toolbox telemetry can include tool parameters, SQL, query results, and errors depending on your Toolbox configuration. Review Data Governance before enabling production traffic.
Then run your MCP Toolbox with telemetry enabled and point it to Agnost AI:
Replace <your-agnost-org-id> with your organization ID from your Agnost AI dashboard. You can set OTEL_EXPORTER_OTLP_HEADERS in your shell profile or environment configuration so it persists across sessions.

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 Raw logs and Tools in Agnost. 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.
  • If tool args/results are sensitive, scrub or disable those fields before production rollout.

Need Help?

MCP Toolbox Support Resources