Home / Servers / DigitalOcean API / genai_create_model_evaluation_run
Create Model Evaluation Run
An MCP tool from the DigitalOcean API server, hosted on mcp.hjlabs.in.
Create Model Evaluation Run To create a model evaluation run, send a POST request to /v2/genai/model_evaluation_runs. [POST /v2/gen-ai/model_evaluation_runs]
Name on the gateway: digitalocean_api__genai_create_model_evaluation_run · may change things.
Parameters
| Name | Type | Description |
|---|---|---|
candidate_inference_config | object | Inference configuration for the candidate model during evaluation. The output… |
candidate_model_name | string | Model slug used to call the candidate model API. For dedicated inference, this… |
candidate_model_source | CANDIDATE_MODEL_SOURCE_SERVERLESS | CANDIDATE_MODEL_SOURCE_DEDICATED | CANDIDATE_MODEL_SOURCE_ROUTER | CANDIDATE_MODEL_SOURCE_AGENT | Whether the candidate is a served model (serverless platform, a dedicated… |
candidate_model_uuid | string | UUID of the candidate model to evaluate. |
dataset_uuid | string | UUID of the dataset to use for evaluation. |
epochs | integer | How many times each dataset row is evaluated. Defaults to 1, maximum 10. When… |
eval_preset_uuid | string | |
judge_model_uuid | string | UUID of the judge model used to score responses. |
metric_uuids | array | UUIDs of metrics to evaluate (selected from ListModelEvaluationMetrics). |
name | string | |
preset_name | string | |
preset_save_sections | array | Which sections of this run's resolved configuration to persist as a reusable… |
save_as_preset | boolean | Deprecated: use preset_save_sections. When true and preset_save_sections is… |
source | string | Source of the run creation (api, sdk, cli). |
star_metric | object |
How to call it
Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:
{
"name": "digitalocean_api__genai_create_model_evaluation_run",
"arguments": {}
}Or connect the DigitalOcean API server directly, which lists 874 tools including this one:
claude mcp add --transport http hj-digitalocean-api https://mcp.hjlabs.in/mcp/digitalocean-api \
--header "Authorization: Bearer YOUR_API_KEY"Try asking
Use the create model evaluation run tool with candidate_inference_config set to ….