# io.github.yasmanycastillo/model-shunt (pypi · model-shunt)

Model routing for AI agents: delegate bulk reads & boilerplate to cheap worker models.

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- npm · `model-shunt`: 39/100, [markdown](https://verifymcp.io/servers/yasmanycastillo-model-shunt/model-shunt-2.md), [page](https://verifymcp.io/servers/yasmanycastillo-model-shunt/model-shunt-2)
- pypi · `model-shunt`: 67/100 (this document), [markdown](https://verifymcp.io/servers/yasmanycastillo-model-shunt/model-shunt.md), [page](https://verifymcp.io/servers/yasmanycastillo-model-shunt/model-shunt)

## Channel facts

- Registry: `pypi`
- Package: `model-shunt`
- Version: `1.2.1`
- 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 2026-09-25.

- **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.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (MIT License) isn't a recognized OSI-approved license.
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 365 tokens (~121/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.yasmanycastillo/model-shunt MCP server?

io.github.yasmanycastillo/model-shunt runs locally as a PyPI package, launched with uvx model-shunt. 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 yasmanycastillo-model-shunt -- uvx model-shunt
```

### Cursor

```json
{
  "mcpServers": {
    "yasmanycastillo-model-shunt": {
      "command": "uvx",
      "args": [
        "model-shunt"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "yasmanycastillo-model-shunt": {
      "command": "uvx",
      "args": [
        "model-shunt"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add yasmanycastillo-model-shunt -- uvx model-shunt
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add yasmanycastillo-model-shunt --command uvx --arg model-shunt
```

### Hermes

```yaml
mcp_servers:
  yasmanycastillo-model-shunt:
    command: "uvx"
    args: ["model-shunt"]
```

### Netclaw

```json
{
  "McpServers": {
    "yasmanycastillo-model-shunt": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "model-shunt"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add yasmanycastillo-model-shunt -t stdio -c uvx -a model-shunt
```

### Other

```json
{
  "mcpServers": {
    "yasmanycastillo-model-shunt": {
      "command": "uvx",
      "args": [
        "model-shunt"
      ]
    }
  }
}
```

## 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.

### 2026-09-25 (score 67, +15)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 52)

First indexed and scored.

## MCP tools (3)

### `bulk_read` (~132 tokens)

Reads multiple or large files and answers a targeted question using a cheap, fast worker model (e.g. Gemini Flash, Groq, Ollama). Saves ~90% tokens by returning only structured bullet points.

Input parameters:

- `file_paths` (array, required): List of file paths to analyze
- `model` (string): Optional model override (or 'auto' to select the best available reader model)
- `provider` (string): Optional provider override (gemini, groq, openai, deepseek, anthropic, ollama, openrouter)
- `question` (string, required): The specific question to answer about the files

### `code_write` (~148 tokens)

Generates boilerplate code (tests, mocks, stubs, configs) matching the patterns of a reference file. Can write directly to disk without consuming frontier output tokens.

Input parameters:

- `model` (string): Optional model override (or 'auto' to select the best available writer model)
- `provider` (string): Optional provider override (gemini, groq, openai, deepseek, anthropic, ollama, openrouter)
- `reference_path` (string, required): Path to reference file whose conventions, style, and structure should be replicated
- `spec` (string, required): Description of what code to generate
- `target_path` (string): Optional path where generated code should be written directly on disk

### `get_available_models` (~85 tokens)

Discovers active models from the worker provider and recommends the best model for reading (high context / low cost) and writing (code intelligence). Enables calling agents to delegate dynamically to the best model.

Input parameters:

- `provider` (string): Optional provider to query (gemini, groq, openai, deepseek, anthropic, ollama, openrouter). Defaults to active provider.

## Diagnostics

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

## Score history

- 2026-09-25: 67
- 2026-09-24: 52

## Common questions

### What is the io.github.yasmanycastillo/model-shunt MCP server?

io.github.yasmanycastillo/model-shunt is an MCP server listed in the public MCP registry as io.github.yasmanycastillo/model-shunt. Model routing for AI agents: delegate bulk reads & boilerplate to cheap worker models. This page covers its PyPI package (model-shunt).

### Is the io.github.yasmanycastillo/model-shunt MCP server safe to use?

io.github.yasmanycastillo/model-shunt scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 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 io.github.yasmanycastillo/model-shunt MCP server expose?

io.github.yasmanycastillo/model-shunt exposes 3 tools: bulk_read, code_write, get_available_models. Their descriptions and schemas cost roughly 365 tokens of context every time the server is loaded.

### Is the io.github.yasmanycastillo/model-shunt MCP server still maintained?

io.github.yasmanycastillo/model-shunt is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- PyPI project: https://pypi.org/project/model-shunt/
- Socket report: https://socket.dev/pypi/package/model-shunt
- Repository: https://github.com/yasmanycastillo/model-shunt
- Changelog RSS feed: https://verifymcp.io/servers/yasmanycastillo-model-shunt/model-shunt.xml
- Changelog JSON feed: https://verifymcp.io/servers/yasmanycastillo-model-shunt/model-shunt.json
- HTML version of this page: https://verifymcp.io/servers/yasmanycastillo-model-shunt/model-shunt