list-experiments-for-dataset
Retrieve a comprehensive list of experiments conducted on a specific dataset, including metadata such as ID, version, project name, and timestamps, for detailed analysis and tracking.
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
| Name | Required | Description | Default |
|---|---|---|---|
| dataset_id | Yes |
Implementation Reference
- Handler function that uses PhoenixClient to GET the list of experiments for the given dataset_id and returns the JSON stringified data as text content.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 defined with Zod: requires a 'dataset_id' string parameter.dataset_id: z.string(), },
- js/packages/phoenix-mcp/src/experimentTools.ts:94-116 (registration)Tool registration via McpServer.tool call, specifying name, description, 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) }, ], }; } );
- Description string for the tool, explaining usage and expected return format.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" } ]`;