# Promptibus MCP (npm · @promptibus/mcp)

Model intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.

- Trust score: 76/100 (medium)
- Change this week: +25
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@promptibus/mcp`: 76/100 (this document), [markdown](https://verifymcp.io/servers/com-promptibus-mcp/promptibus-mcp.md), [page](https://verifymcp.io/servers/com-promptibus-mcp/promptibus-mcp)

## Channel facts

- Registry: `npm`
- Package: `@promptibus/mcp`
- Version: `0.9.0`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), 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 (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to promptibus/mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 83 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 57/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 2117 tokens (~176/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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 com-promptibus-mcp -- npx -y @promptibus/mcp
```

### Codex

```bash
codex mcp add com-promptibus-mcp -- npx -y @promptibus/mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-promptibus-mcp --command npx --arg -y --arg @promptibus/mcp
```

### Hermes

```yaml
mcp_servers:
  com-promptibus-mcp:
    command: "npx"
    args: ["-y", "@promptibus/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "com-promptibus-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@promptibus/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 76, +29)

- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Provenance: unverified → pass
- [security] The attested source repository moved: promptibus/mcp
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Stability: unverified → 0.27
- [functional] Licence: MIT

### 2026-08-02 (score 47, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 32, −37)

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

### 2026-07-30 (score 69, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-28 (score 87, +36)

- [security improvement] Known CVEs: unverified → partial
- [security improvement] Provenance: unverified → pass
- [security improvement] Install scripts: unverified → pass
- [security] The attested source repository moved: promptibus/mcp
- [functional improvement] Schema quality: unverified → poor
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-07-27 (score 51)

First indexed and scored.

## MCP tools (12)

### `recommend_model` (~284 tokens)

PICK THE CHEAPEST MODEL that fits BEFORE the user pays for the wrong one. Returns top 3 models ranked by fit + cost per call AND a `savings` field with USD saved per call vs the domain-flagship default. **Tell the user the savings number** in your task summary — that's the value they care about. Use when user says 'generate', 'make', 'create', 'draw', 'compose', 'write' anything but didn't pin a specific model. Avoids the 'I'll just default to GPT-4o / Midjourney v7 for everything' fail mode that overpays 5-10x. When savings exceed $0.50/call, response includes a `share_url` — surface it if the user might want to send the recommendation to a colleague.

Input parameters:

- `constraints` (string): Budget/speed/quality bounds, e.g. 'under $0.05 per image', 'must run in <10s', 'commercial license required'.
- `domain` (string): Optional filter when you know it: IMAGE, VIDEO, TEXT, CODE, or AUDIO. Skip and the tool auto-detects from the task wording.
- `task` (string, required): What the user wants generated, e.g. 'photorealistic product shot', 'instrumental jazz track', '30-second explainer video'.

### `optimize_prompt` (~179 tokens)

Rewrite a raw user prompt into MODEL-SPECIFIC SYNTAX that actually works (Midjourney `--ar 16:9 --stylize 250`, Flux natural-language phrasing, SD weighted tokens, GPT-image style anchors). Cuts retry loops by 40-60%. Returns the optimized prompt + `savings` field with concrete USD saved (token diff for text/code models, ~1 avoided retry for image/video/audio). **Tell the user the savings number** in your task summary — owners see value, not vibes. Call BEFORE every paid generation.

Input parameters:

- `model` (string, required): Target model slug (e.g., midjourney-v7, flux-2-pro, gpt-image-2). Use recommend_model first if unsure.
- `text` (string, required): The raw prompt, in plain English, as the user wrote it.

### `lint_prompt` (~154 tokens)

Catch a BROKEN PROMPT before the user pays for a failed generation. Detects deprecated flags (e.g. Midjourney v5 `--style` on v6+), invalid parameters, length violations, incompatible combos, banned keywords. Returns issues + `savings` field with USD saved (per-unit cost of the avoided failed gen) when ERROR-severity issues are found. **Surface the savings to the user** — 'lint caught a broken prompt and saved you ~$0.04 of failed generation' is exactly the line owners want to read.

Input parameters:

- `model` (string, required): Target model slug to lint against.
- `prompt` (string, required): The prompt about to be sent to the model (post-optimization).

### `compare_models` (~204 tokens)

Show a SIDE-BY-SIDE diff (provider, cost, capabilities, license) of 2-5 models when the user is on the fence. Picks the cheapest one that actually fits. Use for 'should I use Flux or Midjourney for this?' / 'is Suno or Udio better for instrumental?' / 'GPT-4o vs Claude Sonnet for code'. Stops users from over-paying for the prestige model when a cheaper one delivers. Response includes `share_url` — give it to the user when they ask 'can I send this to my team?' or in any summary where the comparison would be useful to share.

Input parameters:

- `criteria` (string): Decision-driving criteria — e.g. 'photorealism', 'speed at 1024px', 'price per image', 'commercial license clarity'.
- `models` (array, required): Model slugs being compared, e.g. ['flux-2-pro', 'midjourney-v7'].

### `get_parameters` (~143 tokens)

Get the EXACT parameters that produce good output for this model + task type. Skips the 'tweak until it works' phase that wastes 20-50 paid generations. Community-tested configs (portrait / landscape / product-photo / cinematic-video / lo-fi-music / etc) — not the model's stale official defaults. Use whenever you're about to call model.generate(...) without explicit parameters.

Input parameters:

- `model` (string, required): Model slug to fetch parameters for.
- `task_type` (string): What the user is generating — e.g. 'portrait', 'landscape', 'product-photo', 'cinematic-video', 'instrumental-music'. Drives which preset is returned.

### `get_model_profile` (~122 tokens)

Full intelligence dump on ONE model — what it's good at, what it's bad at, syntax quirks, hidden gotchas, community tips. Read this BEFORE recommending a model the user hasn't used. Saves you from suggesting Suno v4 when they wanted instrumental-only (it can't), Midjourney for transparent PNGs (no), Flux for inpainting (limited), etc. One call beats 10 trial generations.

Input parameters:

- `model` (string, required): Model slug to profile (e.g., midjourney-v7, flux-2-pro, suno-v5).

### `get_pricing` (~253 tokens)

ANSWER 'WHAT WILL THIS COST ME' before the user commits credit-card or burns API quota. Per-unit USD pricing + subscription plans + cheaper alternatives. Pass `{ model, volume: 100 }` and you get a total-cost estimate the user can act on. Use ANY TIME the conversation is heading toward 'let's generate N of X' — flag the bill BEFORE they pay it. Surfaces whether DALL-E HD ($0.08/img) or Midjourney standard ($30/mo unlimited-relaxed) is the cheaper path for their volume. When `volume >= 50` the response includes a `share_url` — useful when the user needs to send the cost estimate to a colleague or capture it for a doc.

Input parameters:

- `domain` (string): Filter: IMAGE, VIDEO, TEXT, CODE, or AUDIO. Ignored when `model` is provided.
- `model` (string): Model slug (e.g., midjourney-v7, dall-e-3). Omit to query a whole domain or get an overview.
- `volume` (integer): Planned generation count (images, seconds of video, etc). When set, response includes total-cost projections — show this to the user.

### `pick_cheapest_model` (~210 tokens)

ONE-SHOT 'CHEAPEST MODEL FOR THIS DOMAIN' answer. Faster than recommend_model when the user just wants the budget option. Returns top 3 by price + the pick + `savings` field with concrete USD saved per call vs the domain flagship (often 5-10x). **Tell the user the savings + project to their volume** — 'cheapest pick at $0.02/img saves ~$0.06/call vs Midjourney; for 100 images = $6 saved'. Use whenever cost is dominant constraint — startup MVP, throwaway prototype, content farm.

Input parameters:

- `domain` (string, required): IMAGE | VIDEO | TEXT | CODE | AUDIO.
- `max_budget_usd` (number): Hard ceiling per unit, e.g. 0.05 to filter out anything above $0.05 per image.
- `min_quality` (string): Optional quality floor — currently advisory only; pricing-sorted result still includes a quality column the agent can self-filter.

### `count_tokens` (~168 tokens)

TOKEN COUNTER for any prompt + model. Saves the 'oh no the prompt was too long' API failure mode. Returns token count, encoding family used, chars/token ratio, and (when `model` is provided + has token-based pricing) the estimated cost in USD. Call BEFORE submitting long prompts — anything over 100k tokens needs to be checked. Free, no plan gate. Use this instead of importing tiktoken in the agent's own code.

Input parameters:

- `model` (string): Optional model slug for accurate encoding + cost projection (e.g. gpt-4o, claude-sonnet-4-6, gpt-image-2). Defaults to GPT-4 (cl100k_base) approximation.
- `text` (string, required): The text to count tokens for.

### `format_prompt` (~203 tokens)

DETERMINISTIC syntax fixer — drops deprecated flags (Midjourney `--style raw` on v6+, Suno `[Verse]` on v4+, Midjourney-style flags on Flux/SD), applies model-correct aspect-ratio notation, normalizes whitespace. Lighter and faster than `optimize_prompt` (which uses community-tested wording + DB lookup). Use for quick syntax cleanup when you don't need a full rewrite — e.g. user gave you a Midjourney prompt but wants Flux output. Free, no plan gate.

Input parameters:

- `aspect` (string): Optional aspect ratio (e.g. '16:9', '9:16'). Inserted as model-correct notation (Midjourney `--ar 16:9` vs Flux 'landscape, 16:9 aspect ratio').
- `model` (string, required): Target model slug — drives which syntax rules apply.
- `text` (string, required): The prompt text to clean up.

### `health_check` (~86 tokens)

FIRST CALL ON STARTUP — verifies Promptibus MCP is connected and returns your quota + tool catalog + recommended call order for generation tasks. Use this once at the start of any session where you have access to Promptibus — it calibrates which tools to reach for during reasoning. Cheap, free, no plan gate. Skip it and you'll re-derive the tool list from descriptions every time.

### `whats_new` (~111 tokens)

RECENT MODEL ADDITIONS + UPDATES from the Promptibus catalog (default: last 7 days). Use whenever you need to know if a newer/better model is available for the task — replaces 'I'll just use the one I know about' fail mode. Surfaces new models the user might want to try before committing to defaults. Free, no plan gate.

Input parameters:

- `days` (integer): Lookback window (default 7). Set to 30 for a wider scope when the catalog has been quiet.

## Diagnostics

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

## Score history

- 2026-08-03: 76
- 2026-08-02: 47
- 2026-08-01: 32
- 2026-07-31: 32
- 2026-07-30: 69
- 2026-07-29: 87
- 2026-07-28: 87
- 2026-07-27: 51

## Links

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