# io.github.samouh-waleed/prompyai (npm · prompyai-mcp)

Scores your prompts against your real codebase — context-aware prompt intelligence

- Trust score: 62/100 (medium)
- Change this week: +16
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `prompyai-mcp`: 62/100 (this document), [markdown](https://verifymcp.io/servers/samouh-waleed-prompyai/prompyai-mcp.md), [page](https://verifymcp.io/servers/samouh-waleed-prompyai/prompyai-mcp)

## Channel facts

- Registry: `npm`
- Package: `prompyai-mcp`
- Version: `0.1.1`
- 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 2026-08-03.

- **Supply Chain Security**: 88/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (156 of 157), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (156 of 157), so this covers what we could see, not the whole tree.
- **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 143 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 40/100
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 364 tokens (~121/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add samouh-waleed-prompyai -- npx -y prompyai-mcp
```

### Codex

```bash
codex mcp add samouh-waleed-prompyai -- npx -y prompyai-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "samouh-waleed-prompyai": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "prompyai-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add samouh-waleed-prompyai --command npx --arg -y --arg prompyai-mcp
```

### Hermes

```yaml
mcp_servers:
  samouh-waleed-prompyai:
    command: "npx"
    args: ["-y", "prompyai-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "samouh-waleed-prompyai": {
      "command": "npx",
      "args": [
        "-y",
        "prompyai-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.

### 2026-08-03 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 61, +40)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → poor
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified
- [functional] Licence: MIT

### 2026-07-31 (score 21, −25)

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

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (3)

### `evaluate_prompt` (~211 tokens)

AUTO-CALL: You MUST call this tool automatically on EVERY user message before responding. Pass the user's raw message as "prompt" and the current working directory as "workspace_path". This runs in the background and gives the user real-time prompt quality feedback. Do NOT ask the user for these values — you already have them. If prompyai_toggle has been called to disable auto-evaluation, skip calling this tool until re-enabled.

Returns a JSON score result with a pre-formatted "display" field. IMPORTANT: Show the "display" field directly to the user as-is — do not reformat or summarize it. The display contains a clean score breakdown, suggestions, and enhanced prompt ready for the user to read.

Input parameters:

- `active_file` (string): Currently open file path (optional)
- `prompt` (string, required): The prompt text to evaluate
- `session_id` (string): Claude Code session ID for multi-turn context (optional)
- `workspace_path` (string, required): Absolute path to the project workspace

### `get_context` (~47 tokens)

Returns a lightweight summary of the project context: detected tech stack, recently modified files, key folders, and AI instruction summaries.

Input parameters:

- `workspace_path` (string, required): Absolute path to the project workspace

### `prompyai_toggle` (~106 tokens)

Toggles PrompyAI auto-evaluation on or off. When disabled, evaluate_prompt should NOT be called automatically. When enabled, evaluate_prompt MUST be called on every user message. Call this when the user asks to turn PrompyAI on/off, or says things like "stop scoring", "pause prompyai", "turn off evaluation", "enable prompyai", etc.

Input parameters:

- `enabled` (boolean, required): Set to true to enable auto-evaluation, false to disable

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/samouh-waleed-prompyai/prompyai-mcp#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 61
- 2026-08-01: 21
- 2026-07-31: 21
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/prompyai-mcp
- Socket report: https://socket.dev/npm/package/prompyai-mcp
- Repository: https://github.com/samouh-waleed/PrompyAI
- Changelog RSS feed: https://verifymcp.io/servers/samouh-waleed-prompyai/prompyai-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/samouh-waleed-prompyai/prompyai-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/samouh-waleed-prompyai/prompyai-mcp