@arizeai/phoenix-mcp

# More Cookbooks Use Phoenix Evals to evaluate your application for hallucinations, toxicity, relevance of retrieved documents, and more. ## Classification Eval Walkthroughs * [Hallucination Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_hallucination_classifications.ipynb) * [Toxicity Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_toxicity_classifications.ipynb) * [Summarization Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_summarization_classifications.ipynb) * [User Frustration Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_user_frustration_classifications.ipynb) * [Question-Answering Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_QA_classifications.ipynb) * [Agent Tool Selection Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_agent_tool_selection_classifications.ipynb) * [Agent Tool Parameter Extraction Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_agent_parameter_extraction_classifications.ipynb) * [Agent Tool Calling Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_agent_tool_calling_classifications.ipynb) * [Reference Link Correctness Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_reference_link_correctness_classifications.ipynb) * [Ground Truth vs AI Evals](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_human_vs_ai_classifications.ipynb)