{
  "id": 9604648,
  "title": "MCP Observability: How to Trace Every Tool Call in Production",
  "url": "https://urgent.news/2026/09/24/mcp-observability-how-to-trace-every-tool-call-in-production",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-24T18:33:49.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/rupa_tiwari_dd308948d710f/mcp-observability-how-to-trace-every-tool-call-in-production-21cp"
  },
  "original_language": "en",
  "account": null,
  "summary": "MCP observability refers to the ability to trace every tool call in production, from a prompt through the model's tool selection, into the server, and back. This is crucial for understanding the performance and behavior of AI models in production environments. The 2026-07-28 MCP specification deprecated several components, including protocol-level Logging, Roots, Sampling, and HTTP+SSE, in an effort to create a more standardized and vendor-neutral approach to observability. OpenTelemetry's GenAI semantic conventions now include a dedicated MCP section with defined spans, attributes, and metrics, allowing for better trace context propagation and improved observability of MCP spans. This change aims to address the common issue of incomplete or lackluster signals in production traces, which can lead to misinformed decisions and unflagged issues.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}