list_catalog_models

MCP tool from Tuning Engines Cli by cerebrixos-org

Browse pre-built models and datasets

How to use it

list_catalog_models is exposed by the Tuning Engines Cli MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the list_catalog_models tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Tuning Engines Cli

$npx -y --package tuningengines-cli@latest te auth status

FULL TUNING ENGINES CLI LISTING

Other tools in Tuning Engines Cli (39)

Call chat, Responses, embeddings, or Messages using the configured credential

cancel_evaluation

Cancel a running evaluation

Cancel a running/queued job

catalog_export_status

Check marketplace export progress

Create a dataset from S3

create_evaluation

Run an evaluation against a dataset

Fine-tune an LLM on a GitHub repo. Supports agent selection (Cody, SIERA), quality tier, base model, epochs, S3 export.

Ingest a trace payload without secrets

Check dataset import/processing status

Delete a dataset

Delete a model from cloud storage

doctor_simulate

Simulate inference access, role, endpoint, policy, and resource checks

estimate_evaluation

Cost estimate for an evaluation

Cost estimate before training. Returns cost range, balance, sufficiency check.

evaluation_status

Live evaluation progress

get_catalog_model

Details of a marketplace item

get_inference_jwt

Get JWT token for direct API access

get_inference_token

Exchange an inference key for a short-lived inference JWT

inference_usage

Inference API usage statistics

Live status with GPU minutes, charges, delivery progress

List datasets for training and evaluation

list_evaluations

List model evaluations

list_evaluators

Available evaluators (codeexecution, similarity, llmjudge, etc.)

list_inference_models

Models available for inference

List Insight Loop recommendations

List training jobs with status filter

List trained and imported models

List observed outcomes/goals normalized as success signals

list_supported_models

Available base models with GPU hours per epoch

List runtime traces

Import/export progress

Retry a failed job from its last checkpoint

send_agent_message

Send a governed A2A agent message

Dataset details and status

show_evaluation

Evaluation details, scores, and metrics

Show one Insight Loop recommendation

Full job details including agent, model, GPU usage, cost, retry info

Model details (status, size, base model, training job)

Show a trace with linked events, policy decisions, and approvals