Skip to main content
Glama
Arize-ai

@arizeai/phoenix-mcp

Official
by Arize-ai

list-experiments-for-dataset

Retrieve all experiments conducted on a specific dataset to analyze model performance and track testing iterations.

Instructions

Get a list of all the experiments run on a given dataset.

Experiments are collections of experiment runs, each experiment run corresponds to a single dataset example. The dataset example is passed to an implied task which in turn produces an output.

Example usage: Show me all the experiments I've run on dataset RGF0YXNldDox

Expected return: Array of experiment objects with metadata. Example: [ { "id": "experimentid1234", "dataset_id": "datasetid1234", "dataset_version_id": "datasetversionid1234", "repetitions": 1, "metadata": {}, "project_name": "Experiment-abc123", "created_at": "YYYY-MM-DDTHH:mm:ssZ", "updated_at": "YYYY-MM-DDTHH:mm:ssZ" } ]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataset_idYes

Implementation Reference

  • Handler function that fetches the list of experiments for the given dataset_id using PhoenixClient API and returns the JSON stringified response data.
    async ({ dataset_id }) => { const response = await client.GET( "/v1/datasets/{dataset_id}/experiments", { params: { path: { dataset_id, }, }, } ); return { content: [ { type: "text", text: JSON.stringify(response.data?.data, null, 2) }, ], }; }
  • Registration of the 'list-experiments-for-dataset' MCP tool with server.tool, specifying name, description reference, input schema, and handler function.
    "list-experiments-for-dataset", LIST_EXPERIMENTS_DESCRIPTION, { dataset_id: z.string(), }, async ({ dataset_id }) => { const response = await client.GET( "/v1/datasets/{dataset_id}/experiments", { params: { path: { dataset_id, }, }, } ); return { content: [ { type: "text", text: JSON.stringify(response.data?.data, null, 2) }, ], }; } );
  • Input schema for the tool using Zod: requires 'dataset_id' as string.
    dataset_id: z.string(), },
  • Constant string providing the detailed description for the 'list-experiments-for-dataset' tool.
    const LIST_EXPERIMENTS_DESCRIPTION = `Get a list of all the experiments run on a given dataset. Experiments are collections of experiment runs, each experiment run corresponds to a single dataset example. The dataset example is passed to an implied \`task\` which in turn produces an output. Example usage: Show me all the experiments I've run on dataset RGF0YXNldDox Expected return: Array of experiment objects with metadata. Example: [ { "id": "experimentid1234", "dataset_id": "datasetid1234", "dataset_version_id": "datasetversionid1234", "repetitions": 1, "metadata": {}, "project_name": "Experiment-abc123", "created_at": "YYYY-MM-DDTHH:mm:ssZ", "updated_at": "YYYY-MM-DDTHH:mm:ssZ" } ]`;

Latest Blog Posts

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