# com.synqtune/mcp (pypi · synqtune-mcp)

Fine-tune a small model on your data and benchmark it against your LLM API, in your AWS account.

- Trust score: 59/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `synqtune-mcp`: 59/100 (this document), [markdown](https://verifymcp.io/servers/com-synqtune-mcp/synqtune-mcp.md), [page](https://verifymcp.io/servers/com-synqtune-mcp/synqtune-mcp)

## Channel facts

- Registry: `pypi`
- Package: `synqtune-mcp`
- Version: `0.1.6`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 0 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 6/100
  - Repository check failed: no source repository is declared.
  - Build provenance not yet verified.
  - License check failed: the license (LicenseRef-SynqTune-Proprietary) isn't a recognized OSI-approved license.
  - Actively maintained (last published 0 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 1055 tokens (~131/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the com.synqtune/mcp server?

com.synqtune/mcp runs locally as a PyPI package, launched with uvx synqtune-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add com-synqtune-mcp -- uvx synqtune-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "com-synqtune-mcp": {
      "command": "uvx",
      "args": [
        "synqtune-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-synqtune-mcp": {
      "command": "uvx",
      "args": [
        "synqtune-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-synqtune-mcp -- uvx synqtune-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-synqtune-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "synqtune-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-synqtune-mcp --command uvx --arg synqtune-mcp
```

### Hermes

```yaml
mcp_servers:
  com-synqtune-mcp:
    command: "uvx"
    args: ["synqtune-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-synqtune-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "synqtune-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-synqtune-mcp -t stdio -c uvx -a synqtune-mcp
```

### Other

```json
{
  "mcpServers": {
    "com-synqtune-mcp": {
      "command": "uvx",
      "args": [
        "synqtune-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 59, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-04 (score 43, −15)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.1.5 → 0.1.6

### 2026-11-02 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 57)

First indexed and scored.

## MCP tools (8)

### `list_templates` (~28 tokens)

Task templates a pipeline can start from, with the inputs each needs and the data format it expects.

Output parameters:

- `result` (array)

### `list_runs` (~41 tokens)

Recent pipeline runs, newest first. status: all, running, completed, failed or cancelled.

Input parameters:

- `limit` (integer)
- `status` (string)

Output parameters:

- `result` (array)

### `get_run` (~37 tokens)

Status of one run: current step, progress, error, and a summary of its evaluation and comparison.

Input parameters:

- `run_id` (string, required)

Output parameters:

- `result` (object)

### `get_comparison_report` (~67 tokens)

The comparison between the fine-tuned model and the LLM it should replace: verdict (ready / close / not_ready),
reasons, scores, the weakest labels or fields, and the examples where the fine-tuned model was worse.

Input parameters:

- `run_id` (string, required)

Output parameters:

- `result` (object)

### `list_models` (~17 tokens)

Saved models with their latest and production versions.

Output parameters:

- `result` (array)

### `evaluate_model` (~298 tokens)

Score a saved model version again on a held-out file in S3, optionally against an LLM. Nothing is trained.

version_id: a model version (latest_version_id from list_models). eval_uri: .jsonl, .json or .parquet in the
format the model was trained on, with rows it never trained on. Leave compare_* blank to compare with the LLM
the training run compared with, if any. compare_system_prompt: the prompt the LLM gets in production; blank
keeps the training run's, and with none the LLM is sent the task instruction. inference_engine: what serves the
fine-tuned model in the comparison, huggingface or vllm (blank keeps the training run's); vllm also times the
examples sent 8 and 32 at a time and needs a g5 instance or newer. Without confirm=true this only returns the plan and cost estimate:
show it to the user and call again with confirm=true once they agree; it starts a GPU instance billed to the
user's AWS account.

Input parameters:

- `compare_max_samples`
- `compare_model` (string)
- `compare_provider` (string)
- `compare_system_prompt` (string)
- `confirm` (boolean)
- `eval_uri` (string, required)
- `inference_engine` (string)
- `instance` (string)
- `version_id` (string, required)

Output parameters:

- `result` (object)

### `estimate_cost` (~123 tokens)

GPU cost of a training run (per hour, per day, rough total for the run) and, if you give current LLM usage and
prices, the monthly API spend vs serving the model on the same GPU.

Input parameters:

- `input_tokens`
- `instance` (string)
- `monthly_requests`
- `output_tokens`
- `price_in_per_mtok`
- `price_out_per_mtok`
- `serving_hours_per_day` (number)
- `template` (string)
- `with_comparison` (boolean)

Output parameters:

- `result` (object)

### `launch_pipeline` (~444 tokens)

Train a model from a task template on data in S3, in the user's AWS account.

Without confirm=true this only returns the plan and cost estimate: show it to the user and call again with
confirm=true once they agree. Launching starts GPU instances billed to the user's AWS account.

inputs: the template's inputs (see list_templates), e.g. {"labels": "billing, refund, shipping"}.
compare_*: optionally compare with the LLM the model should replace (provider anthropic, openai or gemini).
The provider key must already be saved in SynqTune under Settings > LLM provider keys; keys are never passed here.
holdout_uri: a held-out file (same format as the source) to test on instead of a random split of the source.
compare_max_samples: how many held-out examples to send to the LLM (default 300).
compare_price_input_per_mtok / compare_price_output_per_mtok: the LLM's USD price per 1M tokens, so the report
shows its cost next to the fine-tuned model's. max_steps, batch_size, base_model: override the template's training.
inference_engine: what serves the fine-tuned model in the comparison, huggingface (default) or vllm. vllm gives
production-like speed and cost, also times requests sent 8 and 32 at a time, and needs a g5 instance or newer.

Input parameters:

- `base_model` (string)
- `batch_size`
- `cloud_account_id` (string)
- `compare_max_samples`
- `compare_model` (string)
- `compare_price_input_per_mtok`
- `compare_price_output_per_mtok`
- `compare_provider` (string)
- `compare_system_prompt` (string)
- `confirm` (boolean)
- `holdout_uri` (string)
- `inference_engine` (string)
- `inputs`
- `instance` (string)
- `max_steps`
- `run_name` (string, required)
- `source_uri` (string, required)
- `template` (string, required)

Output parameters:

- `result` (object)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-synqtune-mcp/synqtune-mcp#diagnostics

## Score history

- 2026-11-05: 59
- 2026-11-04: 43
- 2026-11-03: 58
- 2026-11-02: 58
- 2026-11-01: 57

## Common questions

### What is the com.synqtune/mcp server?

com.synqtune/mcp is listed in the public MCP registry as com.synqtune/mcp. Fine-tune a small model on your data and benchmark it against your LLM API, in your AWS account. This page covers its PyPI package (synqtune-mcp).

### Is the com.synqtune/mcp server safe to use?

com.synqtune/mcp scores 59 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the com.synqtune/mcp server expose?

com.synqtune/mcp exposes 8 tools: list_templates, list_runs, get_run, get_comparison_report, list_models, and 3 more. Their descriptions and schemas cost roughly 1,055 tokens of context every time the server is loaded.

### Is the com.synqtune/mcp server still maintained?

com.synqtune/mcp is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the com.synqtune/mcp server under?

com.synqtune/mcp declares the LicenseRef-SynqTune-Proprietary licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

### What did VerifyMCP test on the com.synqtune/mcp server?

VerifyMCP ran 14 checks on com.synqtune/mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 10 more. 2 items could not be completed, a gap on our side rather than a finding about com.synqtune/mcp: Provenance and Security disclosure. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/synqtune-mcp/
- Socket report: https://socket.dev/pypi/package/synqtune-mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-synqtune-mcp/synqtune-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-synqtune-mcp/synqtune-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-synqtune-mcp/synqtune-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-synqtune-mcp/synqtune-mcp