# Proven (pypi · proven-judge)

Judge AI-written Python: no invented packages or calls, no facts from memory, verified LLM output.

- Trust score: 80/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `proven-judge`: 80/100 (this document), [markdown](https://verifymcp.io/servers/malikabyl-proven/proven-judge.md), [page](https://verifymcp.io/servers/malikabyl-proven/proven-judge)

## Channel facts

- Registry: `pypi`
- Package: `proven-judge`
- Version: `0.2.0`
- 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**: 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.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to malikabyl/proven).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 260 tokens (~86/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 4 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 Proven MCP server?

Proven runs locally as a PyPI package, launched with uvx proven-judge. 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 malikabyl-proven -- uvx proven-judge
```

### Cursor

```json
{
  "mcpServers": {
    "malikabyl-proven": {
      "command": "uvx",
      "args": [
        "proven-judge"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "malikabyl-proven": {
      "command": "uvx",
      "args": [
        "proven-judge"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add malikabyl-proven -- uvx proven-judge
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add malikabyl-proven --command uvx --arg proven-judge
```

### Hermes

```yaml
mcp_servers:
  malikabyl-proven:
    command: "uvx"
    args: ["proven-judge"]
```

### Netclaw

```json
{
  "McpServers": {
    "malikabyl-proven": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "proven-judge"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add malikabyl-proven -t stdio -c uvx -a proven-judge
```

### Other

```json
{
  "mcpServers": {
    "malikabyl-proven": {
      "command": "uvx",
      "args": [
        "proven-judge"
      ]
    }
  }
}
```

## 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 80, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-03 (score 65)

First indexed and scored.

## MCP tools (3)

### `proven_check` (~133 tokens)

Check Python code with Proven

Judge Python code written by AI against hallucinations: invented packages and calls, facts typed from memory, unverified model output, swallowed errors, code without tests. Returns every issue with the rule and how to fix it. Call it after writing or editing Python code and fix every issue until the code is accepted. Note: to check names inside installed packages, Proven imports them (rule P2).

Input parameters:

- `files` (array): Optional: only these files or folders, absolute or relative to the project root.
- `path` (string, required): Absolute path to the project folder (where proven.toml is) or to one file.

### `proven_explain` (~43 tokens)

Explain a Proven rule

Explain one Proven rule (P0-P6): what it requires and how to fix a violation.

Input parameters:

- `code` (string, required): Rule code, for example P4.

### `proven_rules` (~18 tokens)

List the Proven rules

List all Proven rules with their codes and titles.

## Diagnostics

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

## Score history

- 2026-11-05: 80
- 2026-11-04: 65
- 2026-11-03: 65

## Common questions

### What is the Proven MCP server?

Proven is an MCP server listed in the public MCP registry as io.github.malikabyl/proven. Judge AI-written Python: no invented packages or calls, no facts from memory, verified LLM output. This page covers its PyPI package (proven-judge).

### Is the Proven MCP server safe to use?

Proven scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. 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 Proven MCP server expose?

Proven exposes 3 tools: proven_check, proven_explain, proven_rules. Their descriptions and schemas cost roughly 194 tokens of context every time the server is loaded.

### Is the Proven MCP server still maintained?

Proven 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 Proven MCP server under?

Proven 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/proven-judge/
- Socket report: https://socket.dev/pypi/package/proven-judge
- Repository: https://github.com/malikabyl/proven
- Changelog RSS feed: https://verifymcp.io/servers/malikabyl-proven/proven-judge.xml
- Changelog JSON feed: https://verifymcp.io/servers/malikabyl-proven/proven-judge.json
- HTML version of this page: https://verifymcp.io/servers/malikabyl-proven/proven-judge