mcpserver.lol
registry/tuning-engines
Connection check local install

tuning-engines

Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.

Tools 111
GitHub stars 6
Installs / wk 236
Licence MIT
Transport stdio
Last checked never

Tools & capabilities

111 tools

Read from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.

accept_insight from source
apply_insight from source
apply_work_session_repair from source
approve_approval from source
call_inference from source
Call a governed model endpoint using the MCP server
cancel_evaluation from source
Cancel a running or queued evaluation.
cancel_job from source
Cancel a running or queued fine-tuning job. The job will be charged for any GPU time already used.
catalog_export_status from source
Check the status of a Marketplace export operation. Returns status, charge info, and any error messages.
complete_compliance_source_run from source
complete_work_session from source
create_compliance_source_run from source
create_dataset from source
Create dataset metadata for fine-tuning or evaluation.
create_evaluation from source
Create a new model evaluation. Run your trained model or a base model against a dataset using selected evaluators.
create_job from source
Fine-tune an LLM on a GitHub repository using Tuning Engines.
create_runtime_intervention from source
create_trace from source
dataset_status from source
Check the status of a dataset import or processing operation.
delete_dataset from source
Delete a dataset from the platform.
delete_model from source
Delete a trained model from cloud storage.
deny_approval from source
doctor_simulate from source
estimate_evaluation from source
Get a cost estimate for an evaluation before running it.
estimate_job from source
Get a cost estimate for a fine-tuning job before submitting it. Returns estimated cost, cost range, current balance, and whether balance is sufficient. Always estimate before creat…
evaluation_status from source
Get live status of an evaluation including progress and current metrics.
flush_inference_capture from source
generate_policy_draft from source
get_account from source
Get your Tuning Engines account details and settings.
get_balance from source
Check your Tuning Engines account balance and recent transactions.
get_catalog_model from source
Get detailed information about a specific pre-built model or dataset from the Marketplace including description, pricing, and export options.
get_inference_jwt from source
Get a JWT token for authenticating with the Tuning Engines inference API.
get_inference_token from source
Exchange an inference key (sk-te-...) for a short-lived inference JWT.
inference_capture_show from source
inference_capture_update from source
inference_usage from source
Get inference API usage statistics including request counts, token usage, and costs.
install_mcp_template from source
invoke_skill from source
Prepare or invoke a governed skill.
job_status from source
Get live status of a fine-tuning job including current status, GPU minutes used, estimated charges, remaining balance, and delivery progress. Use this to monitor a running job.
list_agents from source
List available agents configured for your organization. Agents are AI assistants with specific capabilities and tool access.
list_approvals from source
list_catalog_models from source
List available pre-built models and datasets from the Tuning Engines Marketplace.
list_compliance_risks from source
list_datasets from source
List datasets available for training and evaluation. Datasets can be uploaded from S3 and used for fine-tuning or model evaluation.
list_evaluations from source
List model evaluations. Evaluations run your trained models against benchmark datasets using various evaluators to measure quality.
list_evaluators from source
List available evaluators for model evaluation. Evaluators measure different aspects of model quality like code execution, similarity, or LLM-based judgment.
list_inference_feedback from source
list_inference_models from source
List models available for inference through the Tuning Engines inference API.
list_initiatives from source
list_insights from source
list_jobs from source
List fine-tuning training jobs on Tuning Engines. Returns recent jobs with status, base model, agent type, GPU usage, and cost. Use this to check on existing training runs or find…
list_mcp_templates from source
list_models from source
List your trained and imported models on Tuning Engines.
list_outcomes from source
list_policy_decisions from source
list_policy_templates from source
list_runtime_interventions from source
list_runtime_state_references from source
list_skills from source
List skills available to the configured inference identity.
list_supported_models from source
List the supported base HuggingFace models available for fine-tuning on Tuning Engines. Optionally filter by agent to see only compatible models.
list_tenant_resources from source
list_traces from source
list_work_sessions from source
map_outcome from source
model_status from source
Check the status of a model import or export operation.
preview_work_session_repair from source
propose_outcome from source
record_inference_feedback from source
record_outcome from source
registry_sync_apply from source
registry_sync_dry_run from source
render_policy_template from source
retry_job from source
Retry a failed fine-tuning job from its last checkpoint. Creates a new job that resumes training where the failed one stopped, saving GPU time. Each retry is billed separately.\n\n
retry_tenant_resource_sync from source
send_agent_message from source
Send a governed message to a registered A2A agent.
show_agent from source
Get details of a specific agent including capabilities, tools, and configuration.
show_approval from source
show_compliance_certification from source
show_compliance_evidence from source
show_compliance_risk from source
show_dataset from source
Get details of a specific dataset including status, source, and metadata.
show_evaluation from source
Get full details of a specific evaluation including status, scores, metrics, and comparison data.
show_initiative from source
show_insight from source
show_job from source
Get full details of a specific fine-tuning job including status, base model, agent type, GPU minutes, cost, error messages, and whether it can be retried from checkpoint.
show_mcp_template from source
show_model from source
Get details of a specific trained model.
show_policy_decision from source
show_registry_sync from source
show_runtime_intervention from source
show_runtime_state_reference from source
show_trace from source
show_work_session from source
submit_compliance_source_results from source
tenant_domains_update from source
tenant_invitation_cancel from source
tenant_resource_create from source
tenant_resource_delete from source
tenant_resource_list from source
tenant_resource_show from source
tenant_resource_update from source
tenant_resource_validate from source
tenant_team_disable from source
tenant_team_enable from source
tenant_team_invite from source
tenant_team_list from source
tenant_team_remove from source
tenant_team_set_inference_role from source
test_governance_policy from source
undo_work_session_repair from source
upsert_runtime_state_reference from source
validate_compliance from source
verify_tenant_secret_reference from source