# Krauncher analyzer (pypi · krauncher-mcp)

How long a GPU job will run and cost, before running it — static code analysis, never executed.

- Trust score: 75/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `krauncher-mcp`: 75/100 (this document), [markdown](https://verifymcp.io/servers/ilya-a-sergeyev-ger-krauncher-mcp/krauncher-mcp.md), [page](https://verifymcp.io/servers/ilya-a-sergeyev-ger-krauncher-mcp/krauncher-mcp)

## Channel facts

- Registry: `pypi`
- Package: `krauncher-mcp`
- Version: `0.5.0`
- 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 2026-09-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 1 of 39 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 37 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 52/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1164 tokens (~1164/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Krauncher analyzer MCP server?

Krauncher analyzer runs locally as a PyPI package, launched with uvx krauncher-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 ilya-a-sergeyev-ger-krauncher-mcp -- uvx krauncher-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "ilya-a-sergeyev-ger-krauncher-mcp": {
      "command": "uvx",
      "args": [
        "krauncher-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ilya-a-sergeyev-ger-krauncher-mcp": {
      "command": "uvx",
      "args": [
        "krauncher-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ilya-a-sergeyev-ger-krauncher-mcp -- uvx krauncher-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ilya-a-sergeyev-ger-krauncher-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "krauncher-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ilya-a-sergeyev-ger-krauncher-mcp --command uvx --arg krauncher-mcp
```

### Hermes

```yaml
mcp_servers:
  ilya-a-sergeyev-ger-krauncher-mcp:
    command: "uvx"
    args: ["krauncher-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ilya-a-sergeyev-ger-krauncher-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "krauncher-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ilya-a-sergeyev-ger-krauncher-mcp -t stdio -c uvx -a krauncher-mcp
```

### Other

```json
{
  "mcpServers": {
    "ilya-a-sergeyev-ger-krauncher-mcp": {
      "command": "uvx",
      "args": [
        "krauncher-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.

### 2026-09-20 (score 75, −3)

- [functional] Stability: pass → 0.80

### 2026-09-19 (score 78, +1)

- [security] Stability: 0.97 → pass

### 2026-09-17 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 76, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-09-14 (score 60, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-13 (score 75, −3)

- [functional] Stability: pass → 0.80

### 2026-09-12 (score 78, +1)

- [security] Stability: 0.97 → pass

### 2026-09-11 (score 77, −1)

- [functional] Stability: pass → 0.97

## MCP tools (1)

### `estimate_gpu_time_and_cost` (~938 tokens)

Runtime, cost and performance analysis of a GPU job, before running it.

Use it to predict how long a training or inference job will take, find what
holds its performance back, see whether the GPU is utilized or left waiting
on the host, and pick the run parameters that make the code faster or
cheaper. Numbers come from a corpus of measured runs — a
runtime reasoned out of source is routinely wrong by several times. The code
is analyzed, never executed: change a parameter, re-estimate, keep the
cheaper variant — zero GPU-seconds.

Returns, on a fixed reference card (RTX PRO 6000 WS): compute_sec /
setup_sec / io_sec, min_vram_gb / min_disk_gb, cpu_only, confidence (0-1),
analysis_method, findings (what the analyzer read from the code), plus
knobs / spread / spread_reason / calibration_basis / iterations /
iteration_basis:

\`knobs` is the shortlist worth re-estimating — change their VALUES ONLY, not
the model, architecture, dataset or procedure. `value: null` means it is not
a literal in this source (it arrives as an argument, a config entry or an
env var), so name it in the code and estimate again. `same_work: false`
(epochs, steps, sequence length) shrinks the job itself: report that as a
change of task, never as a saving.

\`spread` is how far the same code scatters across real hosts: 1.5 means the
slow end of the measured population runs about 1.5x the estimate. It is a
measured factor, not doubt about the reading — confidence 1.0 with a large
spread says the GPU is not what governs this job's time, the card waits on
the host. The lever is GPU utilization: find what leaves the card idle (data
loaded in the main process, per-item preprocessing, synchronous transfers, a
batch too small to fill it). `spread_reason` names it.

\`calibration_basis` is "calibrated", "extrapolated" (a neighbour answered)
or "uncalibrated" (read the seconds as an order of magnitude).

\`iterations` is the step count the whole estimate scales with, and
\`iteration_basis` is where it came fro…

Input parameters:

- `code` (string, required)
- `run_args`

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/ilya-a-sergeyev-ger-krauncher-mcp/krauncher-mcp#diagnostics

## Score history

- 2026-09-20: 75
- 2026-09-19: 78
- 2026-09-18: 77
- 2026-09-17: 77
- 2026-09-16: 76
- 2026-09-15: 76
- 2026-09-14: 60
- 2026-09-13: 75
- 2026-09-12: 78
- 2026-09-11: 77
- 2026-09-10: 78
- 2026-09-09: 77
- 2026-09-08: 77
- 2026-09-07: 64
- 2026-09-06: 64
- 2026-09-05: 64
- 2026-09-04: 64
- 2026-09-03: 64
- 2026-09-02: 64
- 2026-09-01: 64
- 2026-08-31: 64
- 2026-08-30: 64
- 2026-08-29: 64
- 2026-08-28: 64
- 2026-08-27: 64
- 2026-08-26: 64
- 2026-08-25: 61
- 2026-08-24: 61
- 2026-08-23: 61
- 2026-08-22: 61

## Common questions

### What is the Krauncher analyzer MCP server?

Krauncher analyzer is an MCP server listed in the public MCP registry as io.github.Ilya-a-sergeyev-ger/krauncher-mcp. How long a GPU job will run and cost, before running it, static code analysis, never executed. This page covers its PyPI package (krauncher-mcp).

### Is the Krauncher analyzer MCP server safe to use?

Krauncher analyzer scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 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 Krauncher analyzer MCP server expose?

Krauncher analyzer exposes 1 tool: estimate_gpu_time_and_cost. Their descriptions and schemas cost roughly 938 tokens of context every time the server is loaded.

### Is the Krauncher analyzer MCP server still maintained?

Krauncher analyzer is still listed as active in the MCP registry. We last reached this channel on 20 September 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 Krauncher analyzer MCP server under?

Krauncher analyzer declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/krauncher-mcp/
- Socket report: https://socket.dev/pypi/package/krauncher-mcp
- Repository: https://github.com/Ilya-a-sergeyev-ger/krauncher
- Changelog RSS feed: https://verifymcp.io/servers/ilya-a-sergeyev-ger-krauncher-mcp/krauncher-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ilya-a-sergeyev-ger-krauncher-mcp/krauncher-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ilya-a-sergeyev-ger-krauncher-mcp/krauncher-mcp