It can write code and answer questions — but it can't tell you the right Midjourney V8 parameters, Suno V5 tag syntax, or Runway Gen-4 physics prompting. Promptibus MCP gives it that knowledge.
guidance_scale: 3.5, steps: 28, aspect_ratio: "1:1"ChatGPT, Claude, and Gemini know the world of text. They don't know the specific syntax, parameters, and constraints of the models that actually generate images, video, audio, and code.
--oref, --ow, --sref, --cref, --personalize
Omni-reference, style reference, character reference — undocumented in LLM training data
[Verse], [Drop], [Falsetto], genre tags
Metatag processing that controls song structure and vocal style
Physics-based prompting, camera motion syntax
Describing physical interactions and camera moves that Gen-4 actually understands
LoRA triggers, negative prompts, sampler configs
Model-specific keywords, weighting syntax like (word:1.3), and sampler parameters
The result: your agent guesses. 3-5 attempts instead of 1. Wasted API calls, wasted credits, bad outputs.
67
AI models tracked
5
domains
760+
curated prompts
Weekly
data updates
Each tool returns structured data with links back to promptibus.com for full model guides, community tips, and prompt galleries.
recommend_modelrecommend_model(task, constraints)
ask: "Product photos on white background, budget under $0.05/image"
get: Flux 2.0 Pro — API-native, $0.04/image, 28-step generation, built-in background removal
format_promptformat_prompt(text, model)
ask: "A cat floating in space" → Midjourney V8
get: cosmic feline drifting weightlessly through nebula, bioluminescent fur, volumetric starlight --ar 16:9 --s 350 --style raw --v 8
compare_modelscompare_models(models[], criteria)
ask: ["midjourney-v8", "flux-2-pro", "dall-e-3"] for "photorealism"
get: Side-by-side: resolution, pricing, API access, photorealism rating, strengths/weaknesses
get_parametersget_parameters(model, task_type)
Add Promptibus MCP to any MCP-compatible client. The server ships as an npm package — no API keys needed for the free tier.
{
"mcpServers": {
"promptibus": {
"command": "npx",
"args": ["@promptibus/mcp"]
}
}
}The MCP server is currently in development. Configuration above is final — it will work exactly like this on launch.
We want every agent using Promptibus. The free tier covers most use cases. Pay only when you need higher limits or advanced tools.
25 calls/day · 500/month
500 calls/day · 10,000/month
760+ prompts and model tips contributed by practitioners who use these models daily. Not scraped docs — real working knowledge.
Midjourney V8 shipped last month. Suno V5 changed tag syntax. LLM training data is months behind. Promptibus data updates weekly.
As of April 2026, no other MCP server provides model intelligence for generative AI. Search MCP, web MCP, code MCP — model MCP is ours.
Yes. The free tier gives you 25 calls/day with access to the 10 most popular models and core tools (recommend_model, format_prompt). No credit card required.
Pro and Studio tiers get updates weekly — the same day we verify new model changes. Free tier updates monthly. Model profiles always reflect the latest verified information.
67 models across 5 domains: image (Midjourney, Flux, DALL-E, Stable Diffusion), video (Runway, Sora, Kling), audio (Suno, Udio, ElevenLabs), text (ChatGPT, Claude, Gemini), and code (Copilot, Cursor, Claude Code).
Yes. Every model guide on promptibus.com accepts community edits. Contributions from the web app feed directly into MCP responses — your tips help every agent using the server.
Free tier works without a key (25 calls/day). Create a free account and generate an API key to get 100 calls/day. Pro and Studio plans unlock all tools and models.
The MCP server is in active development. Join the waitlist to get notified on launch day. The configuration and tool signatures shown on this page are final.
Promptibus MCP is launching soon. Create an account now and you'll be first to know.
ask: "midjourney-v8" for "portrait"
get: --ar 2:3 --s 250 --style raw --cref [url] --cw 80 — with explanation of each param
validate_promptvalidate_prompt(prompt, model)
ask: "ultra realistic photo --v 5 --quality 3" for Midjourney V8
get: Issues: --v 5 deprecated (use --v 8), --quality max is 2. Suggested fix included.
get_model_profileget_model_profile(model)
ask: "suno-v5"
get: Full profile: capabilities, syntax guide, tag reference, pricing, limitations, tips from community
browse resourcesMCP resources
ask: promptibus://models/midjourney-v8
get: Model profiles as MCP resources — browsable by any MCP-compatible client
2,000 calls/day · 50,000/month
MCP access is part of your Promptibus subscription — not a separate product. See full plan comparison · Get your API key