Rendrkit

Created By
vbiff4 months ago
Design API for AI Agents. Generate social media images, marketing banners, infographics, and documents from text prompts or structured data. 50+ templates, 5 sizes, Unsplash/Pexels photos. One API call - any visual.
Overview

@rendrkit/mcp

MCP (Model Context Protocol) server for RendrKit. Lets AI assistants like Claude Desktop and Cursor generate professionally designed images via the RendrKit API.

Installation

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "rendrkit": {
      "command": "npx",
      "args": ["-y", "@rendrkit/mcp"],
      "env": {
        "RENDRKIT_API_KEY": "rk_your_api_key_here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "rendrkit": {
      "command": "npx",
      "args": ["-y", "@rendrkit/mcp"],
      "env": {
        "RENDRKIT_API_KEY": "rk_your_api_key_here"
      }
    }
  }
}

Windsurf

Add to your Windsurf MCP config (~/.codeium/windsurf/mcp_config.json):

{
  "mcpServers": {
    "rendrkit": {
      "command": "npx",
      "args": ["-y", "@rendrkit/mcp"],
      "env": {
        "RENDRKIT_API_KEY": "rk_your_api_key_here"
      }
    }
  }
}

Available Tools

generate_image

Generate a professionally designed image from a text description. Creates production-ready images with clean layouts, crisp text, and consistent branding. Perfect for social media posts, banners, OG images, thumbnails, and more.

ParameterTypeRequiredDescription
promptstringYesDescription of the image to generate
sizestringNoImage dimensions (e.g. 1080x1080, 1200x628, 1280x720)
styleenumNoVisual style: modern, playful, corporate, dark, minimal, bold
brand_kit_idstringNoID of a saved brand kit to use for consistent branding

get_image

Get details of a previously generated image.

ParameterTypeRequiredDescription
idstringYesThe image ID

list_brand_kits

List all saved brand kits. Brand kits contain colors, fonts, and logos for consistent image generation. No parameters required.

get_usage

Check current usage statistics including images generated this month and plan limits. No parameters required.

Environment Variables

VariableRequiredDefaultDescription
RENDRKIT_API_KEYYes-Your RendrKit API key (starts with rk_)
RENDRKIT_BASE_URLNohttps://api.rendrkit.devAPI base URL (for self-hosted or development)

Development

# Build
npm run build

# Watch mode
npm run dev

License

MIT

Server Config

{
  "mcpServers": {
    "rendrkit": {
      "command": "npx",
      "args": [
        "-y",
        "@rendrkit/mcp@latest"
      ],
      "env": {
        "RENDRKIT_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}
Project Info
Created At
4 months ago
Updated At
3 months ago
Author Name
vbiff
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Wpnews

18 hours ago
Linkpulse

2 days ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

a day ago
Shippo
@Shippo

2 days ago
Orkestr

19 hours ago