mcpField
T
tuning-engines

tuning-engines

Local
github.com/cerebrixos-orgAI & Agents
Repository

About tuning-engines

Tuning Engines is a governed runtime and CLI for teams managing AI workflows. It combines policy-controlled inference, approvals, tracing, and code-model fine-tuning through one control plane.

Key features

  1. 01OpenAI-compatible inference API
  2. 02RBAC, traffic policies, and approvals
  3. 03Trace, usage, and cost analytics
  4. 04Fine-tuning from code repositories
  5. 05Training job and evaluation management

Use cases

  1. 01Centralize model access and risky-action review
  2. 02Train autocomplete models on a codebase
  3. 03Train repository-specific bug-fix models
  4. 04Inspect agent workflow traces and usage

MCP support

Its built-in MCP server offers 60+ tools for managing fine-tuning jobs, evaluations, usage, traces, approvals, and non-secret tenant metadata. It does not expose internal proxy routes or allow inference-key creation and raw secret-bearing mutations through MCP.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "cerebrixos-tuning-engines": {
      "command": "npx",
      "args": [
        "-y",
        "tuningengines-cli"
      ],
      "env": {
        "TE_API_KEY": "<TE_API_KEY>"
      }
    }
  }
}
Run commandnpx -y tuningengines-cli
Environment variables to set
TE_API_KEYSecretTuning Engines API key. Get one at https://tuningengines.com or by running 'te auth login'.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmtuningengines-cli0.3.5

Tools

101

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
limitnumberNoMax results (default 20)
statusstringNoFilter by status: queued, running, succeeded, failed, canceled

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.