Train domain-specific LLM models on your proprietary data without managing infrastructure. Built for developers who need sovereign, fine-tuned models with minimal setup.
io.github.cerebrixos/tuning-engines
Local install
STDIO
1 required env var
How models use it and what it is built for.
Train domain-specific LLM models on your proprietary data without managing infrastructure. Built for developers who need sovereign, fine-tuned models with minimal setup.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Tuning Engines API key. Get one at https://tuningengines.com or by running 'te auth login'.
Where to find authoritative docs and source for Cerebrixos Tuning Engines.
Paste any of these into Agent Studio after connecting Cerebrixos Tuning Engines.
Common questions about connecting and running Cerebrixos Tuning Engines.
What does the Tuning Engines MCP server do?
It lets you programmatically fine-tune domain-specific LLM models on your own data through an MCP interface, without provisioning or managing infrastructure. You authenticate with an API key and submit training jobs directly from your chat or application.
How do I get a Tuning Engines API key?
Visit https://tuningengines.com to sign up and generate an API key, or run 'te auth login' from the CLI. Set the key as the TE_API_KEY environment variable before using the MCP server.
Do I need to manage servers or GPUs to use this?
No. Tuning Engines handles all infrastructure—you just provide your data and an API key. The service trains and hosts your sovereign model, so you focus on integration, not ops.
What data formats and domains does this support?
The registry describes it as domain-specific fine-tuning on your data. Check the official docs at https://tuningengines.com for supported input formats, model architectures, and domain examples.
Can I use this for real-time inference after training?
The MCP server is designed for fine-tuning workflows. Refer to Tuning Engines documentation to confirm whether trained models are immediately available for inference and what the latency/throughput guarantees are.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams