# Promptibus MCP

Model intelligence for AI agents — syntax, parameters, pricing, and routing for 67+ generative AI models (Midjourney, Flux, Suno, Runway, DALL-E, Stable Diffusion). 7 tools for any MCP client.

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add promptibus/mcp

# Browse available tools
npx -y @smithery/cli@latest tool list promptibus/mcp

# Get full schema for a tool
npx -y @smithery/cli@latest tool get promptibus/mcp recommend_model

# Call a tool
npx -y @smithery/cli@latest tool call promptibus/mcp recommend_model '{}'
```

## Direct MCP Connection

Endpoint: `https://mcp--promptibus.run.tools`

**Optional config:**
- `PROMPTIBUS_API_KEY` (query) — Promptibus API key (starts with psy_). Get one at https://promptibus.com/settings/api-keys

## Tools (7)

- `recommend_model` — Recommend the best AI model for a task. Returns top 3 models with reasoning, parameters, and links.
- `optimize_prompt` — Optimize a prompt for a specific AI model. Applies model-specific syntax, community-tested parameters, and best-practic…
- `lint_prompt` — Lint a prompt against a model's rules. Finds errors like deprecated flags, invalid parameters, or length violations, an…
- `compare_models` — Compare 2-5 AI models side-by-side on provider, domain, cost, and capabilities.
- `get_parameters` — Get recommended parameters for a model, including defaults, ranges, and community-tested configs.
- `get_model_profile` — Get a complete model profile: capabilities, syntax guide, parameters, community tips, and related prompts.
- `get_pricing` — Get real-world USD pricing for an AI model, a whole domain, or a planned generation volume. Returns per-unit cost, subs…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get promptibus/mcp <tool-name>
```

## Resources

- `promptibus://models/dall-e-3` — OpenAI's image model with best-in-class text rendering and natural language prompt understanding.
- `promptibus://models/firefly-3` — Firefly 3 by Adobe. Domain: IMAGE.
- `promptibus://models/flux-1-1-pro` — High-quality open-weight image model excelling at photorealism and text rendering.
- `promptibus://models/flux-2-pro` — 32B parameter model by BFL. State-of-the-art image generation and editing up to 4MP. Precise text rendering, color matc…
- `promptibus://models/gemini-imagen-3` — Google's native image generation via Gemini with exceptional prompt adherence and JSON prompt support.
- `promptibus://models/gpt-image-1` — OpenAI's latest image generation model integrated into ChatGPT with strong text rendering.
- `promptibus://models/gpt-image-1-5` — OpenAI's latest image model. 4x faster than GPT Image 1, precise edits, better consistency. Available in ChatGPT and vi…
- `promptibus://models/ideogram-2` — Specializes in typography and graphic design renders with accurate text placement.
- `promptibus://models/ideogram-3` — Leading model for text-in-image generation. Exceptional typography, graphic design, and logo creation capabilities.
- `promptibus://models/imagen-4-ultra` — Google's top-tier image model. Exceptional photorealism, text rendering, and compositional accuracy. Available via Vert…
- `promptibus://models/leonardo-phoenix` — Leonardo Phoenix by Leonardo AI. Domain: IMAGE.
- `promptibus://models/midjourney-v6` — Industry-leading image generation with exceptional aesthetic quality and prompt adherence.
- `promptibus://models/midjourney-v7` — Midjourney's smartest and most coherent model. Enhanced prompt understanding, voice prompting, draft mode for rapid ite…
- `promptibus://models/playground-v3` — Playground v3 by Playground. Domain: IMAGE.
- `promptibus://models/recraft-v3` — Design-focused image model excelling at vector illustrations, icons, and brand-consistent assets.
- `promptibus://models/recraft-v4-pro` — Professional design-focused model. Brand-consistent outputs, style presets, and vector-quality illustrations.
- `promptibus://models/sdxl-1-0` — Versatile open-source model with a massive ecosystem of fine-tunes, LoRAs, and community tools.
- `promptibus://models/sd-3-5` — Next-gen architecture with improved coherence and detail over SDXL.
- `promptibus://models/hailuo-ai` — Hailuo AI by Minimax. Domain: VIDEO.
- `promptibus://models/helios` — 14B autoregressive diffusion model generating 60-second videos at real-time speed on a single GPU.
- `promptibus://models/kling-1-5` — Chinese video model with impressive motion quality and longer generation times.
- `promptibus://models/kling-2-5` — Major upgrade with improved motion quality, longer clips, and better facial expressions. Cost-effective for social medi…
- `promptibus://models/ltx-2-3` — Open-source 22B diffusion transformer. Native 4K video with synchronized audio generation in a single pass.
- `promptibus://models/luma-dream-machine` — Luma Dream Machine by Luma. Domain: VIDEO.
- `promptibus://models/minimax-video` — Chinese video model known for consistent character identity and long-form generation.
- `promptibus://models/pika-2` — Fast video generation with good creative control and image-to-video capabilities.
- `promptibus://models/pika-3` — Enhanced creative effects, improved scene generation, and new 'Scenes' feature for multi-shot storytelling.
- `promptibus://models/runway-gen-3` — Professional video generation with precise motion control and camera direction.
- `promptibus://models/runway-gen-4` — Runway's latest with improved temporal consistency, camera control, and up to 20-second coherent clips.
- `promptibus://models/seedance-2` — ByteDance's video generation model with high motion quality and dance/movement specialization.
- `promptibus://models/sora` — OpenAI's video generation model producing cinematic-quality clips from text prompts.
- `promptibus://models/veo-2` — Google's video generation model producing high-fidelity clips with cinematic camera control.
- `promptibus://models/claude-4-5-haiku` — Fastest Claude model with near-Sonnet quality. Extended thinking, computer use, image understanding. One-third the cost…
- `promptibus://models/claude-4-opus` — Anthropic's most powerful model — exceptional at analysis, writing, and code generation.
- `promptibus://models/claude-4-sonnet` — Balanced performance model — fast, capable, and cost-effective for most tasks.
- `promptibus://models/claude-sonnet-4-6` — Near-Opus performance at Sonnet pricing. Anthropic's best balance of intelligence, speed, and cost for production use.
- `promptibus://models/command-r-plus` — Command R+ by Cohere. Domain: TEXT.
- `promptibus://models/deepseek-r2` — Open-source reasoning model rivaling frontier closed models. Exceptional at math, code, and step-by-step reasoning.
- `promptibus://models/gemini-2-5-pro` — Google's flagship model with native multimodal reasoning and massive context window.
- `promptibus://models/gemini-3-1-pro` — Google's frontier model. Leading scores on 13/16 benchmarks. 2M+ context window, native multimodal, Google Search groun…
- `promptibus://models/gpt-4o` — Multimodal model excelling at reasoning, coding, and natural conversation.
- `promptibus://models/gpt-5` — OpenAI's most capable model with advanced reasoning and tool use.
- `promptibus://models/gpt-5-4` — Latest GPT-5 variant with 1.05M token context, 33% fewer factual errors. Standard, Thinking, and Pro variants available.
- `promptibus://models/grok-3` — xAI's reasoning model with real-time X/Twitter data access and strong analytical capabilities.
- `promptibus://models/llama-4` — Meta's open-weight frontier model — free to use, fine-tune, and deploy at any scale.
- `promptibus://models/llama-4-maverick` — Meta's 400B MoE model with 128 experts. Strong multilingual, long-context, and instruction-following capabilities.
- `promptibus://models/mistral-large` — Mistral Large by Mistral. Domain: TEXT.
- `promptibus://models/qwen-3` — Qwen 3 by Alibaba. Domain: TEXT.

---
*Response truncated. Use `npx -y @smithery/cli@latest` for complete data.*