Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.
Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics. The tuning engines mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 6 defined tools rather than through you.
Tuning Engines uses specialized agents that control how your data is analyzed and converted into training data. Each agent produces a different kind of domain-specific fine-tuned model optimized for its use case. Current agents focus on code, with more coming for customer support, data extraction, security review, ops, and other domains.
Installation goes through your MCP client rather than a global install: point it at tuningengines-cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Everything the assistant can do here goes through one of these:
Authentication — The Authentication tool exposed by this serverModels — The Models tool exposed by this serverDatasets — The Datasets tool exposed by this serverEvaluations — The Evaluations tool exposed by this serverInference — The Inference tool exposed by this serverAgents — The Agents tool exposed by this serverYou will need one environment variable: TE_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Tuning Engines's toolset — Authentication, Models, Datasets and 3 more — is a fair guide to whether it matches your workflow. It is maintained by cerebrixos-org; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Authentication | The Authentication tool exposed by this server. |
| Models | The Models tool exposed by this server. |
| Datasets | The Datasets tool exposed by this server. |
| Evaluations | The Evaluations tool exposed by this server. |
| Inference | The Inference tool exposed by this server. |
| Agents | The Agents tool exposed by this server. |
{
"mcpServers": {
"tuning-engines": {
"command": "npx",
"args": ["-y", "tuningengines-cli"],
"env": {
"TE_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| TE_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.