@arizeai/phoenix-mcp

# Table of contents * [Arize Phoenix](README.md) * [Quickstarts](quickstart.md) * [User Guide](user-guide.md) * [Environments](environments.md) * [Phoenix Demo](https://phoenix-demo.arize.com/projects) * [Production Guide](production-guide.md) ## Tracing * [Overview: Tracing](tracing/llm-traces/README.md) * [Projects](tracing/llm-traces/projects.md) * [Sessions](tracing/llm-traces/sessions.md) * [Annotations](tracing/llm-traces/how-to-annotate-traces.md) * [Metrics](tracing/llm-traces/metrics.md) * [Quickstart: Tracing](tracing/llm-traces-1/README.md) * [Quickstart: Tracing (Python)](tracing/llm-traces-1/quickstart-tracing-python.md) * [Quickstart: Tracing (TS)](tracing/llm-traces-1/quickstart-tracing-ts.md) * [Features: Tracing](tracing/features-tracing.md) * [How-to: Tracing](tracing/how-to-tracing/README.md) * [Setup Tracing](tracing/how-to-tracing/setup-tracing/README.md) * [Setup using Phoenix OTEL](tracing/how-to-tracing/setup-tracing/setup-using-phoenix-otel.md) * [Setup using base OTEL](tracing/how-to-tracing/setup-tracing/custom-spans.md) * [Using Phoenix Decorators](tracing/how-to-tracing/setup-tracing/instrument-python.md) * [Setup Tracing (TS)](tracing/how-to-tracing/setup-tracing/javascript.md) * [Setup Projects](tracing/how-to-tracing/setup-tracing/setup-projects.md) * [Setup Sessions](tracing/how-to-tracing/setup-tracing/setup-sessions.md) * [Add Metadata](tracing/how-to-tracing/add-metadata/README.md) * [Add Attributes, Metadata, Users](tracing/how-to-tracing/add-metadata/customize-spans.md) * [Instrument Prompt Templates and Prompt Variables](tracing/how-to-tracing/add-metadata/instrumenting-prompt-templates-and-prompt-variables.md) * [Annotate Traces](tracing/how-to-tracing/feedback-and-annotations/README.md) * [Annotating in the UI](tracing/how-to-tracing/feedback-and-annotations/annotating-in-the-ui.md) * [Annotating via the Client](tracing/how-to-tracing/feedback-and-annotations/capture-feedback.md) * [Annotating Auto-Instrumented Spans](tracing/how-to-tracing/feedback-and-annotations/annotating-auto-instrumented-spans.md) * [Running Evals on Traces](tracing/how-to-tracing/feedback-and-annotations/evaluating-phoenix-traces.md) * [Log Evaluation Results](tracing/how-to-tracing/feedback-and-annotations/llm-evaluations.md) * [Importing & Exporting Traces](tracing/how-to-tracing/importing-and-exporting-traces/README.md) * [Import Existing Traces](tracing/how-to-tracing/importing-and-exporting-traces/importing-existing-traces.md) * [Export Data & Query Spans](tracing/how-to-tracing/importing-and-exporting-traces/extract-data-from-spans.md) * [Exporting Annotated Spans](tracing/how-to-tracing/importing-and-exporting-traces/exporting-annotated-spans.md) * [Cost Tracking](tracing/how-to-tracing/cost-tracking/README.md) * [Advanced](tracing/how-to-tracing/advanced/README.md) * [Mask Span Attributes](tracing/how-to-tracing/advanced/masking-span-attributes.md) * [Suppress Tracing](tracing/how-to-tracing/advanced/suppress-tracing.md) * [Filter Spans to Export](tracing/how-to-tracing/advanced/modifying-spans.md) * [Capture Multimodal Traces](tracing/how-to-tracing/advanced/multimodal-tracing.md) * [Concepts: Tracing](tracing/concepts-tracing/README.md) * [What are Traces](tracing/concepts-tracing/what-are-traces.md) * [How Tracing Works](tracing/concepts-tracing/how-tracing-works.md) * [Annotations Concepts](tracing/concepts-tracing/annotations-concepts.md) * [FAQs: Tracing](tracing/concepts-tracing/faqs-tracing.md) ## Prompt Engineering * [Overview: Prompts](prompt-engineering/overview-prompts.md) * [Prompt Management](prompt-engineering/overview-prompts/prompt-management.md) * [Prompt Playground](prompt-engineering/overview-prompts/prompt-playground.md) * [Span Replay](prompt-engineering/overview-prompts/span-replay.md) * [Prompts in Code](prompt-engineering/overview-prompts/prompts-in-code.md) * [Quickstart: Prompts](prompt-engineering/quickstart-prompts/README.md) * [Quickstart: Prompts (UI)](prompt-engineering/quickstart-prompts/quickstart-prompts-ui.md) * [Quickstart: Prompts (Python)](prompt-engineering/quickstart-prompts/quickstart-prompts-python.md) * [Quickstart: Prompts (TS)](prompt-engineering/quickstart-prompts/quickstart-prompts-ts.md) * [How to: Prompts](prompt-engineering/how-to-prompts/README.md) * [Configure AI Providers](prompt-engineering/how-to-prompts/configure-ai-providers.md) * [Using the Playground](prompt-engineering/how-to-prompts/using-the-playground.md) * [Create a prompt](prompt-engineering/how-to-prompts/create-a-prompt.md) * [Test a prompt](prompt-engineering/how-to-prompts/test-a-prompt.md) * [Tag a prompt](prompt-engineering/how-to-prompts/tag-a-prompt.md) * [Using a prompt](prompt-engineering/how-to-prompts/using-a-prompt.md) * [Concepts: Prompts](prompt-engineering/concepts-prompts/README.md) * [Prompts Concepts](prompt-engineering/concepts-prompts/prompts-concepts.md) * [Context Engineering Basics](prompt-engineering/concepts-prompts/context-engineering-basics.md) ## Datasets & Experiments * [Overview: Datasets & Experiments](datasets-and-experiments/overview-datasets.md) * [Quickstart: Datasets & Experiments](datasets-and-experiments/quickstart-datasets.md) * [How-to: Datasets](datasets-and-experiments/how-to-datasets/README.md) * [Creating Datasets](datasets-and-experiments/how-to-datasets/creating-datasets.md) * [Exporting Datasets](datasets-and-experiments/how-to-datasets/exporting-datasets.md) * [How-to: Experiments](datasets-and-experiments/how-to-experiments/README.md) * [Run Experiments](datasets-and-experiments/how-to-experiments/run-experiments.md) * [Using Evaluators](datasets-and-experiments/how-to-experiments/using-evaluators.md) * [Repetitions](datasets-and-experiments/how-to-experiments/repetitions.md) * [Concepts: Datasets](datasets-and-experiments/concepts-datasets.md) ## Evaluation * [Overview: Evals](evaluation/llm-evals/README.md) * [Executors](evaluation/llm-evals/executors.md) * [Evaluator Traces](evaluation/llm-evals/evaluator-traces.md) * [Use Any LLM](evaluation/llm-evals/use-any-llm.md) * [Quickstart: Evals](evaluation/evals.md) * [Concepts: Evals](evaluation/concepts-evals/README.md) * [Eval Data Types](evaluation/concepts-evals/evaluation-types.md) * [LLM as a Judge](evaluation/concepts-evals/llm-as-a-judge.md) * [Custom Task Evaluation](evaluation/concepts-evals/building-your-own-evals.md) * [Evaluating Multi-Agent Systems](evaluation/concepts-evals/evaluating-multi-agent-systems.md) * [Evaluators](evaluation/concepts-evals/evaluators.md) * [Input Mapping](evaluation/concepts-evals/input-mapping.md) * [How to: Evals](evaluation/how-to-evals/README.md) * [Custom LLM Evaluators](evaluation/how-to-evals/custom-llm-evaluators.md) * [Configuring the LLM](evaluation/how-to-evals/configuring-the-llm.md) * [Heuristic Evaluators](evaluation/how-to-evals/heuristic-evaluators.md) * [Batch Evaluations](evaluation/how-to-evals/batch-evaluations.md) * [Using Evals with Phoenix](evaluation/how-to-evals/using-evals-with-phoenix.md) * [Pre-Built Evals](evaluation/running-pre-tested-evals/README.md) * [Heuristic Metrics](evaluation/running-pre-tested-evals/heuristic-metrics.md) * [Hallucination](evaluation/running-pre-tested-evals/hallucinations.md) * [Q\&A on Retrieved Data](evaluation/running-pre-tested-evals/q-and-a-on-retrieved-data.md) * [Retrieval (RAG) Relevance](evaluation/running-pre-tested-evals/retrieval-rag-relevance.md) * [Summarization](evaluation/running-pre-tested-evals/summarization-eval.md) * [Code Generation](evaluation/running-pre-tested-evals/code-generation-eval.md) * [Toxicity](evaluation/running-pre-tested-evals/toxicity.md) * [AI vs Human (Groundtruth)](evaluation/running-pre-tested-evals/ai-vs-human-groundtruth.md) * [Reference (citation) Link](evaluation/running-pre-tested-evals/reference-link-evals.md) * [User Frustration](evaluation/running-pre-tested-evals/user-frustration.md) * [SQL Generation Eval](evaluation/running-pre-tested-evals/sql-generation-eval.md) * [Agent Function Calling Eval](evaluation/running-pre-tested-evals/tool-calling-eval.md) * [Agent Path Convergence](evaluation/running-pre-tested-evals/agent-path-convergence.md) * [Agent Planning](evaluation/running-pre-tested-evals/agent-planning.md) * [Agent Reflection](evaluation/running-pre-tested-evals/agent-reflection.md) * [Audio Emotion Detection](evaluation/running-pre-tested-evals/audio-emotion-detection.md) ## Settings * [Access Control (RBAC)](settings/access-control-rbac.md) * [API Keys](settings/api-keys.md) * [Data Retention](settings/data-retention.md) * [Phoenix to Arize AX Migration](settings/phoenix-to-arize-ax-migration.md) ## Resources * [Frequently Asked Questions](resources/frequently-asked-questions/README.md) * [What is the difference between Phoenix and Arize?](resources/frequently-asked-questions/what-is-the-difference-between-phoenix-and-arize.md) * [What is my Phoenix Endpoint?](resources/frequently-asked-questions/what-is-my-phoenix-endpoint.md) * [What is LlamaTrace vs Phoenix Cloud?](resources/frequently-asked-questions/what-is-llamatrace-vs-phoenix-cloud.md) * [Phoenix Cloud Migration Guide: Legacy to New Version](resources/frequently-asked-questions/phoenix-cloud-migration-guide-legacy-to-new-version.md) * [Will Phoenix Cloud be on the latest version of Phoenix?](resources/frequently-asked-questions/will-phoenix-cloud-be-on-the-latest-version-of-phoenix.md) * [Can I add other users to my Phoenix Instance?](resources/frequently-asked-questions/can-i-add-other-users-to-my-phoenix-instance.md) * [Can I use Azure OpenAI?](resources/frequently-asked-questions/can-i-use-azure-openai.md) * [Can I use Phoenix locally from a remote Jupyter instance?](resources/frequently-asked-questions/can-i-use-phoenix-locally-from-a-remote-jupyter-instance.md) * [How can I configure the backend to send the data to the phoenix UI in another container?](resources/frequently-asked-questions/how-can-i-configure-the-backend-to-send-the-data-to-the-phoenix-ui-in-another-container.md) * [Can I run Phoenix on Sagemaker?](resources/frequently-asked-questions/can-i-run-phoenix-on-sagemaker.md) * [Can I persist data in a notebook?](resources/frequently-asked-questions/can-i-persist-data-in-a-notebook.md) * [What is the difference between GRPC and HTTP?](resources/frequently-asked-questions/what-is-the-difference-between-grpc-and-http.md) * [Can I use gRPC for trace collection?](resources/frequently-asked-questions/can-i-use-grpc-for-trace-collection.md) * [How do I resolve Phoenix Evals showing NOT\_PARSABLE?](resources/frequently-asked-questions/how-do-i-resolve-phoenix-evals-showing-not_parsable.md) * [Braintrust Open Source Alternative? LLM Evaluation Platform Comparison](resources/frequently-asked-questions/braintrust-open-source-alternative-llm-evaluation-platform-comparison.md) * [Langfuse alternative? Arize Phoenix vs Langfuse: key differences](resources/frequently-asked-questions/langfuse-alternative-arize-phoenix-vs-langfuse-key-differences.md) * [Open Source LangSmith Alternative: Arize Phoenix vs. LangSmith](resources/frequently-asked-questions/open-source-langsmith-alternative-arize-phoenix-vs.-langsmith.md) * [Contribute to Phoenix](resources/contribute-to-phoenix.md) * [Github](https://github.com/Arize-ai/phoenix) * [OpenInference](https://github.com/Arize-ai/openinference)