{
  "markdown": "# @promptibus/mcp — model intelligence for AI agents\n\n[![npm version](https://img.shields.io/npm/v/@promptibus/mcp.svg)](https://www.npmjs.com/package/@promptibus/mcp)\n[![npm downloads](https://img.shields.io/npm/dm/@promptibus/mcp.svg)](https://www.npmjs.com/package/@promptibus/mcp)\n[![Smithery](https://smithery.ai/badge/@promptibus/mcp)](https://smithery.ai/server/@promptibus/mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n[![MCP](https://img.shields.io/badge/MCP-compatible-0a7cff.svg)](https://modelcontextprotocol.io)\n[![Powered by Promptibus](https://img.shields.io/badge/powered%20by-promptibus.com-0a7cff.svg)](https://promptibus.com/mcp)\n[![LobeHub MCP Badge](https://lobehub.com/badge/mcp/promptibus-mcp)](https://lobehub.com/mcp/promptibus-mcp)\n\n> Your agent thinks Midjourney still uses `--v 5`. It doesn't — that flag was dropped at v7.\n> It assumes DALL-E 3 and FLUX Schnell cost the same. They differ by ~50×.\n> It confidently writes `[Verse]` tags for Suno. They were removed in v4.\n>\n> **This MCP server fixes that.** Real syntax, real prices, real recommendations for 67+ generative AI models — over the Model Context Protocol.\n\n---\n\n**Works with:** Claude Desktop · Claude Code · Cursor · Windsurf · Zed · Continue.dev · n8n · any stdio MCP client\n**Domains:** image · video · audio · text · code\n**Cost to start:** $0, no account, no API key\n\n## See it in action\n\nYour agent receives a brief — *\"30-second cinematic video of a thunderstorm at sea.\"* — and instead of guessing, calls a tool.\n\n```\nrecommend_model({ task: \"30s cinematic video, thunderstorm at sea\", domain: \"VIDEO\" })\n```\n\n```\nTop 3 models for: \"30s cinematic video, thunderstorm at sea\"\n\n1. Runway Gen-4 (Runway)\n   Domain: VIDEO | Cost: 1 credit | Version: latest\n   Improved temporal consistency, camera control, up to 20-second coherent clips.\n   Source: https://promptibus.com/models/runway-gen-4\n\n2. Sora (OpenAI)\n   Domain: VIDEO | Cost: 1 credit | Version: latest\n   Cinematic-quality clips from text prompts.\n   Source: https://promptibus.com/models/sora\n\n3. Veo 2 (Google)\n   Domain: VIDEO | Cost: 1 credit | Version: latest\n   High-fidelity clips with cinematic camera control.\n   Source: https://promptibus.com/models/veo-2\n```\n\nThe agent picks one, formats the prompt with `optimize_prompt`, lints the result with `lint_prompt`, checks `get_pricing` for the volume budget — all before a single token of generation cost is spent.\n\n## Why use this\n\n- **Stops hallucination.** Your agent answers from a curated DB of 67+ models, not from training data that's 6 months stale.\n- **Real money, real choices.** `get_pricing({ model: \"dall-e-3\", volume: 100 })` returns actual USD cost plus cheaper alternatives — agents can finally optimize for budget, not just \"vibes.\"\n- **Right model for the job.** `recommend_model` ranks across all five domains (image / video / audio / text / code) with reasoning, not guessing.\n- **Lint before you generate.** `lint_prompt` catches deprecated flags, invalid parameters, and length violations *before* you burn credits.\n- **Zero friction.** Works anonymously without an account. `npx -y @promptibus/mcp` — that's the install.\n\n## Install in 30 seconds\n\n**Option A — Smithery (recommended):**\n\nVisit [smithery.ai/server/@promptibus/mcp](https://smithery.ai/server/@promptibus/mcp), pick your client, click install.\n\n**Option B — drop into your client's MCP config:**\n\n```json\n{\n  \"mcpServers\": {\n    \"promptibus\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@promptibus/mcp\"]\n    }\n  }\n}\n```\n\n**Option C — hosted HTTP endpoint (no install at all):**\n\nFor clients that support HTTP transport:\n\n```json\n{\n  \"mcpServers\": {\n    \"promptibus\": {\n      \"url\": \"https://promptibus.com/api/mcp\"\n    }\n  }\n}\n```\n\nPer-client paths are listed under [Client configs](#client-configs) below.\n\n## Tools\n\nEvery tool is available on every tier — including anonymous. Tiering applies to daily request limits and which models you can query against (free-tier covers 10 popular models; Pro/Studio unlocks all 67+).\n\n| Tool | What it does | Example |\n|---|---|---|\n| `recommend_model` | Top 3 models for a task, with reasoning + cost. | `{ task: \"logo with embedded text\", domain: \"IMAGE\" }` |\n| `optimize_prompt` | Reformats a prompt for a specific model — applies model-specific syntax + community-tested wording. | `{ text: \"a cat in space\", model: \"midjourney-v7\" }` |\n| `lint_prompt` | Finds deprecated flags, invalid parameters, length violations. Suggests fixes. | `{ prompt: \"a cat --ar 16:9\", model: \"flux-2-pro\" }` |\n| `compare_models` | Side-by-side: provider, domain, cost, capabilities. 2–5 models. | `{ models: [\"flux-2-pro\",\"midjourney-v7\"], criteria: \"photorealism\" }` |\n| `get_parameters` | Recommended parameters: defaults, ranges, community configs. | `{ model: \"stable-diffusion-3-5\", task_type: \"portrait\" }` |\n| `get_model_profile` | Full profile: capabilities, syntax guide, parameters, community tips, related prompts. | `{ model: \"suno-v4\" }` |\n| `get_pricing` | Real USD pricing for a model / domain / planned volume. Includes cheaper alternatives. | `{ model: \"dall-e-3\", volume: 100 }` |\n\n## Use cases\n\n**\"Which video model gives me the longest single shot under $10?\"**\n→ `get_pricing({ domain: \"VIDEO\", volume: 60 })` returns a sorted matrix; agent picks the cheapest that meets duration.\n\n**\"Convert this DALL-E prompt to Midjourney v7 syntax.\"**\n→ `optimize_prompt({ text: \"...\", model: \"midjourney-v7\" })` reformats — proper aspect-ratio flag, no `--v`, model-specific suffixes applied.\n\n**\"Will this Suno prompt work with v4?\"**\n→ `lint_prompt({ prompt: \"[Verse] ...\", model: \"suno-v4\" })` flags `[Verse]` as deprecated and proposes the v4 structure.\n\n**\"I need to generate 1000 images at the cheapest viable quality.\"**\n→ `recommend_model` filters by domain + budget; `get_pricing` validates total cost; agent ships under budget.\n\n## Resources\n\nBrowsable model profiles as MCP resources:\n\n```\npromptibus://models/{slug}\n```\n\nEach resource returns a Markdown profile (provider, domain, version, pricing, full guide). Useful for agents that want to surface model info as a sidebar.\n\n## Prompts\n\nThe `system-prompt` MCP prompt exposes curated system prompts from the Promptibus community.\n\n```\nsystem-prompt                                         # lists all available\nsystem-prompt { \"slug\": \"midjourney-prompt-architect\" } # returns full text\n```\n\n## Plans & rate limits\n\nAnonymous users get full tool access — no account needed. Limits + model coverage scale with plan.\n\n| Plan | Daily requests | Model coverage |\n|---|---|---|\n| Anonymous (no key) | 25 | 10 free-tier models |\n| Free (with key) | 100 | 10 free-tier models |\n| Pro | 500 | All 67+ models |\n| Studio | 2,000 | All 67+ models |\n\nLimits reset daily at midnight UTC. Plans + signup at [promptibus.com/pricing](https://promptibus.com/pricing).\n\n## Authentication\n\nSet `PROMPTIBUS_API_KEY` in your client config:\n\n```json\n{\n  \"mcpServers\": {\n    \"promptibus\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@promptibus/mcp\"],\n      \"env\": { \"PROMPTIBUS_API_KEY\": \"psy_your_api_key_here\" }\n    }\n  }\n}\n```\n\n| Variable | Required | Purpose |\n|---|---|---|\n| `PROMPTIBUS_API_KEY` | No | Higher rate limits, full model coverage. Get one at [promptibus.com/settings/api-keys](https://promptibus.com/settings/api-keys). |\n| `PROMPTIBUS_API_URL` | No | Override the API base (default `https://promptibus.com`). For self-hosted Promptibus or staging. |\n\n## FAQ\n\n**Does this generate images, video, or audio?**\nNo. It tells your agent *how* to use whatever generation API the agent already has access to. Think of it as a prompt engineering co-pilot, not a router.\n\n**Do I need an account to start?**\nNo. Anonymous mode works out of the box (25 req/day, free-tier models). API key raises limits and unlocks all 67+ models.\n\n**Are my prompts logged?**\nTool requests transit `promptibus.com` over HTTPS. We don't persist prompt bodies. API keys are SHA-256 hashed server-side; the raw key never lands in logs.\n\n**How fresh is the model data?**\nCommunity-curated. New models typically appear within days of release; pricing is reviewed monthly. The data lives in a Postgres-backed catalogue at [promptibus.com/models](https://promptibus.com/models).\n\n**Does it work offline?**\nThe MCP server runs locally; the catalogue lives at promptibus.com. So: agent ↔ MCP server is local stdio, MCP server ↔ Promptibus is HTTPS. No internet, no answers.\n\n**Can I self-host the catalogue?**\nYes. The Promptibus app is open-source — clone [promptibus/promptibus](https://github.com/promptibus/promptibus), point `PROMPTIBUS_API_URL` at your deployment.\n\n**Is there an HTTP transport instead of stdio?**\nYes — point your client at `https://promptibus.com/api/mcp`. Useful for sandboxed environments, browser-based MCP clients, and CI.\n\n## Caching\n\nThe client caches responses for tools whose output rarely changes (`get_model_profile`, `get_parameters`, `compare_models`, `get_pricing`). TTL: 24 h, in-memory per process. Cache is bypassed for tools whose output is input-dependent (`recommend_model`, `optimize_prompt`, `lint_prompt`).\n\n## Privacy\n\n- HTTPS to `promptibus.com`; no third-party trackers in the request path\n- API keys hashed server-side (SHA-256)\n- Anonymous usage rate-limited by IP\n- No client-side database, no local state beyond a single HTTP client\n\n## Client configs\n\nThe same `npx -y @promptibus/mcp` command works for every stdio client. Only the config file location and JSON shape differ.\n\n<details>\n<summary><strong>Claude Desktop</strong></summary>\n\n`~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n  \"mcpServers\": {\n    \"promptibus\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@promptibus/mcp\"]\n    }\n  }\n}\n```\n</details>\n\n<details>\n<summary><strong>Claude Code</strong></summary>\n\n```bash\nclaude mcp add promptibus -- npx -y @promptibus/mcp\n```\n</details>\n\n<details>\n<summary><strong>Cursor</strong></summary>\n\n`.cursor/mcp.json` (project) or `~/.cursor/mcp.json` (global):\n\n```json\n{\n  \"mcpServers\": {\n    \"promptibus\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@promptibus/mcp\"]\n    }\n  }\n}\n```\n</details>\n\n<details>\n<summary><strong>Windsurf</strong></summary>\n\n`~/.codeium/windsurf/mcp_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"promptibus\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@promptibus/mcp\"]\n    }\n  }\n}\n```\n</details>\n\n<details>\n<summary><strong>Zed</strong></summary>\n\n`settings.json`:\n\n```json\n{\n  \"context_servers\": {\n    \"promptibus\": {\n      \"command\": {\n        \"path\": \"npx\",\n        \"args\": [\"-y\", \"@promptibus/mcp\"]\n      }\n    }\n  }\n}\n```\n</details>\n\n<details>\n<summary><strong>Continue.dev</strong></summary>\n\n`~/.continue/config.json`, under `experimental.modelContextProtocolServers`:\n\n```json\n{\n  \"transport\": {\n    \"type\": \"stdio\",\n    \"command\": \"npx\",\n    \"args\": [\"-y\", \"@promptibus/mcp\"]\n  }\n}\n```\n</details>\n\n<details>\n<summary><strong>n8n</strong></summary>\n\nIn the **MCP Client** node, set transport to **stdio**:\n\n```\nCommand:   npx\nArguments: -y @promptibus/mcp\n```\n</details>\n\n## Supported models\n\n**67+ models across 5 domains.** Highlights:\n\n- **IMAGE** — Midjourney v7 / v6.1 · FLUX 2 Pro / 1.1 Pro · Stable Diffusion 3.5 · DALL-E 3 · GPT Image 1 · Ideogram 3 · Recraft V4 Pro · Imagen 4 Ultra · Leonardo Phoenix\n- **VIDEO** — Sora · Runway Gen-3 / Gen-4 · Kling 2.5 · Pika 3 · Luma Dream Machine · Hailuo · Seedance 2 · Veo 2 · LTX 2.3 · Helios\n- **AUDIO** — Suno v4 / v5 · Udio 2 · ElevenLabs · Hume AI · Stable Audio 2 · MusicGen · ACE-Step\n- **TEXT** — GPT-5 / 5.4 · Claude 4 Opus / Sonnet · Claude Sonnet 4.6 · Gemini 3.1 Pro / 2.5 Pro · DeepSeek R2 · Llama 4 Maverick · Grok 3\n- **CODE** — Claude Code · Cursor · Windsurf · Codex CLI · Devin · Augment Code · Aider · Copilot · DeepSeek V3 · Nemotron 3 Super\n\nFull catalogue: [promptibus.com/models](https://promptibus.com/models).\n\n## ⭐ Help others find this\n\nIf `@promptibus/mcp` saves your agent from a wrong-syntax run or a $50 surprise on DALL-E volume, [drop a star](https://github.com/promptibus/mcp) on the repo. Stars are how new MCP users discover quality servers in a sea of generic wrappers — it costs you a click and the next person ships faster.\n\n[![Star this repo](https://img.shields.io/github/stars/promptibus/mcp?style=social)](https://github.com/promptibus/mcp/stargazers)\n\n## Links\n\n- **Website:** [promptibus.com](https://promptibus.com)\n- **All models:** [promptibus.com/models](https://promptibus.com/models)\n- **API keys:** [promptibus.com/settings/api-keys](https://promptibus.com/settings/api-keys)\n- **Pricing:** [promptibus.com/pricing](https://promptibus.com/pricing)\n- **Issues:** [github.com/promptibus/mcp/issues](https://github.com/promptibus/mcp/issues)\n- **Main app source:** [github.com/promptibus/promptibus](https://github.com/promptibus/promptibus)\n- **MCP spec:** [modelcontextprotocol.io](https://modelcontextprotocol.io)\n\n## License\n\nMIT — © Promptibus\n",
  "bytes": 13093,
  "sha": "428087f1c2b2481f351a7236ad61bfde30417df9f0dd2e03d44b787527181e67",
  "repo_slug": "promptibus/mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_promptibus_mcp_3d2cb130/readme"
}