How do I connect Tuning Engines Cli MCP Server to Claude?

Run `claude mcp add tuning-engines-cli -- npx -y --package tuningengines-cli@latest te auth status` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.

Is Tuning Engines Cli MCP Server free?

The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.

What can Tuning Engines Cli MCP Server do?

Tuning Engines Cli MCP Server documents 40 tools to the agent, including call_inference, cancel_evaluation, cancel_job. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.

Tuning Engines Cli

Unclaimed

by cerebrixos-org

CLI & MCP server for Tuning Engines — fine-tune LLMs on code repositories

Set up this server

Compare servers My Stack

01 / Choose your client

02 / Before you connect

Authentication is not specified. Check the project instructions before connecting.

Install the runtime required by the project and make it available to your client.

Project instructionsEnvironment variable names (optional)

Use names from the project instructions, separated by commas. Enter names only, never secret values.

03 / Add the configuration

Source: generated from public install instructions

claude mcp add --transport stdio 'tuning-engines-cli' -- 'npx' '-y' '--package' 'tuningengines-cli@latest' 'te' 'auth' 'status'

Run in your terminal after replacing any placeholders.

04 / Check it in your client

Open your client’s MCP settings and confirm the server connects and lists its tools. A copied configuration does not confirm a working connection.

aiclidsh-pluginfine-tuningllmloramachine-learningmcpmcp-servermodel-context-protocolopen-sourceqloraslmsovereign-ai

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

40 of 40 tools

Documented tools (40)

From project documentation. A server handshake does not verify each tool’s description or behavior.

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

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about Tuning Engines Cli MCP Server

How do I connect Tuning Engines Cli MCP Server to Claude?: Run `claude mcp add tuning-engines-cli -- npx -y --package tuningengines-cli@latest te auth status` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.
Is Tuning Engines Cli MCP Server free?: The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can Tuning Engines Cli MCP Server do?: Tuning Engines Cli MCP Server documents 40 tools to the agent, including call_inference, cancel_evaluation, cancel_job. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.