Tuning Engines Cli
未认领CLI & MCP server for Tuning Engines — fine-tune LLMs on code repositories
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'tuning-engines-cli' -- 'npx' '-y' '--package' 'tuningengines-cli@latest' 'te' 'auth' 'status'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
40 个工具中显示 40 个
文档中列出的工具 (40)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
call_inference
Call chat, Responses, embeddings, or Messages using the configured credential
cancel_evaluation
Cancel a running evaluation
cancel_job
Cancel a running/queued job
catalog_export_status
Check marketplace export progress
create_dataset
Create a dataset from S3
create_evaluation
Run an evaluation against a dataset
create_job
Fine-tune an LLM on a GitHub repo. Supports agent selection (Cody, SIERA), quality tier, base model, epochs, S3 export.
create_trace
Ingest a trace payload without secrets
dataset_status
Check dataset import/processing status
delete_dataset
Delete a dataset
delete_model
Delete a model from cloud storage
doctor_simulate
Simulate inference access, role, endpoint, policy, and resource checks
estimate_evaluation
Cost estimate for an evaluation
estimate_job
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
job_status
Live status with GPU minutes, charges, delivery progress
list_catalog_models
Browse pre-built models and datasets
list_datasets
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_insights
List Insight Loop recommendations
list_jobs
List training jobs with status filter
list_models
List trained and imported models
list_outcomes
List observed outcomes/goals normalized as success signals
list_supported_models
Available base models with GPU hours per epoch
list_traces
List runtime traces
model_status
Import/export progress
retry_job
Retry a failed job from its last checkpoint
send_agent_message
Send a governed A2A agent message
show_dataset
Dataset details and status
show_evaluation
Evaluation details, scores, and metrics
show_insight
Show one Insight Loop recommendation
show_job
Full job details including agent, model, GPU usage, cost, retry info
show_model
Model details (status, size, base model, training job)
show_trace
Show a trace with linked events, policy decisions, and approvals