# io.github.CloudCorpRecords/modelrun (npm · @reneturcios/modelrun)

Replicate models, collections, versions, and predictions: browse and run.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@reneturcios/modelrun`: 65/100 (this document), [markdown](https://verifymcp.io/servers/cloudcorprecords-modelrun/reneturcios-modelrun.md), [page](https://verifymcp.io/servers/cloudcorprecords-modelrun/reneturcios-modelrun)
- oci · `ghcr.io/cloudcorprecords/modelrun`: 42/100, [markdown](https://verifymcp.io/servers/cloudcorprecords-modelrun/ghcr-io-cloudcorprecords-modelrun.md), [page](https://verifymcp.io/servers/cloudcorprecords-modelrun/ghcr-io-cloudcorprecords-modelrun)

## Channel facts

- Registry: `npm`
- Package: `@reneturcios/modelrun`
- Version: `0.1.0`
- 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 2026-11-05.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 93 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 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 540 tokens (~49/item across 11 items; 11 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 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 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.

**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.CloudCorpRecords/modelrun MCP server?

io.github.CloudCorpRecords/modelrun runs locally as an npm package, launched with npx -y @reneturcios/modelrun. 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 cloudcorprecords-modelrun -- npx -y @reneturcios/modelrun
```

### Cursor

```json
{
  "mcpServers": {
    "cloudcorprecords-modelrun": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/modelrun"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cloudcorprecords-modelrun": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/modelrun"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add cloudcorprecords-modelrun -- npx -y @reneturcios/modelrun
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cloudcorprecords-modelrun": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@reneturcios/modelrun"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cloudcorprecords-modelrun --command npx --arg -y --arg @reneturcios/modelrun
```

### Hermes

```yaml
mcp_servers:
  cloudcorprecords-modelrun:
    command: "npx"
    args: ["-y", "@reneturcios/modelrun"]
```

### Netclaw

```json
{
  "McpServers": {
    "cloudcorprecords-modelrun": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@reneturcios/modelrun"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add cloudcorprecords-modelrun -t stdio -c npx -a -y @reneturcios/modelrun
```

### Other

```json
{
  "mcpServers": {
    "cloudcorprecords-modelrun": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/modelrun"
      ]
    }
  }
}
```

## 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.

### 2026-11-03 (score 65, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 50)

First indexed and scored.

## MCP tools (11)

### `list_models` (~47 tokens)

List models on Replicate, one page at a time, with an optional pagination cursor.

Input parameters:

- `cursor` (string): Optional pagination cursor from a previous response to fetch the next page of models.

### `get_model` (~57 tokens)

Fetch one model by owner and name, including its description and latest version summary.

Input parameters:

- `name` (string, required): The name of the model to fetch.
- `owner` (string, required): The owner (user or organization) of the model to fetch.

### `list_collections` (~18 tokens)

List the curated model collections on Replicate.

### `get_collection` (~35 tokens)

Fetch one collection by slug, including the models it contains.

Input parameters:

- `slug` (string, required): The slug identifier of the collection to fetch.

### `list_model_versions` (~57 tokens)

List the versions of one model by owner and name.

Input parameters:

- `name` (string, required): The name of the model whose versions to list.
- `owner` (string, required): The owner (user or organization) of the model whose versions to list.

### `get_model_version` (~68 tokens)

Fetch one version of one model, including its input/output schema.

Input parameters:

- `name` (string, required): The name of the model.
- `owner` (string, required): The owner (user or organization) of the model.
- `versionId` (string, required): The identifier of the specific model version to fetch.

### `create_prediction` (~125 tokens)

Create a prediction: run a model version (version) or an official model (model, as owner/name) with the given input object, and an optional webhook.

Input parameters:

- `input` (object, required): The model's input object, passed through unchanged to the prediction.
- `model` (string): Optional official model to run as 'owner/name'; exactly one of version or model must be given.
- `version` (string): Optional model version ID to run; exactly one of version or model must be given.
- `webhook` (string): Optional webhook URL to notify when the prediction completes.

### `get_prediction` (~35 tokens)

Fetch one prediction by ID, including its status and output.

Input parameters:

- `predictionId` (string, required): The identifier of the prediction to fetch.

### `list_predictions` (~47 tokens)

List predictions for the account, one page at a time, with an optional pagination cursor.

Input parameters:

- `cursor` (string): Optional pagination cursor from a previous response to fetch the next page of predictions.

### `cancel_prediction` (~31 tokens)

Cancel a running prediction by ID.

Input parameters:

- `predictionId` (string, required): The identifier of the running prediction to cancel.

### `get_account` (~20 tokens)

Fetch the account that owns the configured Replicate API token.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/cloudcorprecords-modelrun/reneturcios-modelrun#diagnostics

## Score history

- 2026-11-05: 65
- 2026-11-04: 65
- 2026-11-03: 65
- 2026-11-02: 50

## Common questions

### What is the io.github.CloudCorpRecords/modelrun MCP server?

io.github.CloudCorpRecords/modelrun is an MCP server listed in the public MCP registry as io.github.CloudCorpRecords/modelrun. Replicate models, collections, versions, and predictions: browse and run. This page covers its npm package (@reneturcios/modelrun).

### Is the io.github.CloudCorpRecords/modelrun MCP server safe to use?

io.github.CloudCorpRecords/modelrun scores 65 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. 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.CloudCorpRecords/modelrun MCP server expose?

io.github.CloudCorpRecords/modelrun exposes 11 tools: list_models, get_model, list_collections, get_collection, list_model_versions, and 6 more. Their descriptions and schemas cost roughly 540 tokens of context every time the server is loaded.

### Is the io.github.CloudCorpRecords/modelrun MCP server still maintained?

io.github.CloudCorpRecords/modelrun 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 io.github.CloudCorpRecords/modelrun MCP server under?

io.github.CloudCorpRecords/modelrun 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

- npm package: https://www.npmjs.com/package/@reneturcios/modelrun
- Socket report: https://socket.dev/npm/package/@reneturcios/modelrun
- Repository: https://github.com/CloudCorpRecords/modelrun
- Changelog RSS feed: https://verifymcp.io/servers/cloudcorprecords-modelrun/reneturcios-modelrun.xml
- Changelog JSON feed: https://verifymcp.io/servers/cloudcorprecords-modelrun/reneturcios-modelrun.json
- HTML version of this page: https://verifymcp.io/servers/cloudcorprecords-modelrun/reneturcios-modelrun