Home / Servers / OpenAI API / get_eval_run_output_items

Get eval run output items

An MCP tool from the OpenAI API server, hosted on mcp.hjlabs.in.

Get eval run output items Get a list of output items for an evaluation run. [GET /evals/{eval_id}/runs/{run_id}/output_items]

Name on the gateway: openai_api__get_eval_run_output_items · read-only.

Parameters

Name	Type	Description
`eval_id` required	`string`	The ID of the evaluation to retrieve runs for.
`run_id` required	`string`	The ID of the run to retrieve output items for.
`after`	`string`	Identifier for the last output item from the previous pagination request.
`limit`	`integer`	Number of output items to retrieve.
`status`	`fail \| pass`	Filter output items by status. Use failed to filter by failed output items or…
`order`	`asc \| desc`	Sort order for output items by timestamp. Use asc for ascending order or desc…

Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:

call_tool arguments

{
  "name": "openai_api__get_eval_run_output_items",
  "arguments": {
    "eval_id": "…",
    "run_id": "…"
  }
}

Or connect the OpenAI API server directly, which lists 371 tools including this one:

Run in your terminal

claude mcp add --transport http hj-openai-api https://mcp.hjlabs.in/mcp/openai-api \
  --header "Authorization: Bearer YOUR_API_KEY"

Use the get eval run output items tool with eval_id set to ….