Skip to main content
Glama

@arizeai/phoenix-mcp

Official
by Arize-ai
features-tracing.md1.04 kB
--- description: >- Tracing is a critical part of AI Observability and should be used both in production and development --- # Features: Tracing Phoenix's tracing and span analysis capabilities are invaluable during the prototyping and debugging stages. By instrumenting application code with Phoenix, teams gain detailed insights into the execution flow, making it easier to identify and resolve issues. Developers can drill down into specific spans, analyze performance metrics, and access relevant logs and metadata to streamline debugging efforts. <figure><img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/phoenix_tracing.png" alt=""><figcaption><p>View the inner workings for your LLM Application</p></figcaption></figure> This section contains details on Tracing features: * [projects.md](llm-traces/projects.md "mention") * [how-to-annotate-traces.md](llm-traces/how-to-annotate-traces.md "mention") * [sessions.md](llm-traces/sessions.md "mention") * [metrics.md](llm-traces/metrics.md "mention")

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Arize-ai/phoenix'

If you have feedback or need assistance with the MCP directory API, please join our Discord server