Skip to main content
📖 The AI Tool Bible

EverArt MCP Server vs MCP Everything Server

A side-by-side look at pricing, capabilities, pros, cons, and our editorial scores.

 EverArt MCP Server logo
EverArt MCP Server
MCP Servers
MCP Everything Server logo
MCP Everything Server
MCP Servers
TaglineArchived MCP server that lets Claude and MCP clients generate images via EverArt's FLUX, SD 3.5 and Recraft models.The kitchen-sink reference MCP server that exercises every corner of the Model Context Protocol
CategoryMCP ServersMCP Servers
PricingFree· MCP server is free and open source; requires an EverArt account and API key (EverArt itself is a paid image-generation service with credit-based pricing).Free· Free and open source (MIT License). No cloud service or paid tier — you run it locally via npx, Docker, or your MCP client of choice.
ModelFLUX 1.1, FLUX 1.1 Ultra, Stable Diffusion 3.5, Recraft (Real and Vector) via EverArt—
Editorial score——
Use cases
In-chat image generation from Claude DesktopIDE-driven mockup and illustration generation in VS CodePrompt-to-image reference art for design brainstormingAgent-invoked cover art and thumbnail generationReference implementation for building custom image-API MCP serversQuick FLUX 1.1 Ultra renders inside an LLM workflow
MCP client conformance testingRegression testing of stdio and Streamable HTTP transportsVerifying sampling round-trip behavior in a new agent hostDebugging elicitation UI in an IDE integrationReference reading for authoring a new MCP serverDemoing MCP primitives in workshops and talksSmoke-testing cancellation and progress-notification handlingValidating resource-subscription update delivery
Pros
  • Drop-in MCP server that lets Claude Desktop or VS Code generate images through natural-language tool calls
  • Exposes five current image models (FLUX 1.1, FLUX 1.1 Ultra, SD 3.5, Recraft Real, Recraft Vector) through a single tool
  • Tiny TypeScript codebase makes it a useful reference for building your own image-API MCP wrapper
  • Installs via npx or Docker with a one-click VS Code button, so setup is a few minutes
  • Open source under the MCP servers repo license, easy to fork and extend
  • Only server that exercises the full MCP feature matrix in one place — tools, resources, prompts, sampling, elicitation, roots, logging, subscriptions, and Tasks
  • Maintained by the Model Context Protocol project itself, so behavior tracks the spec as it evolves (SEP-1686 Tasks, Streamable HTTP, etc.)
  • Runs anywhere an MCP client runs — npx, Docker, Claude Desktop, VS Code, Cursor, Windsurf — with stdio or HTTP transports
  • TypeScript source is short and readable, making it a de-facto reference for how each handler should be shaped
  • MIT-licensed, no telemetry, no signup, no cloud dependency
  • Includes progress notifications and cancellation flows that most tutorial servers skip, so client cancel/timeout logic can be exercised properly
Cons
  • Officially archived in May 2025 and no longer maintained upstream
  • Only one tool (generate_image) with no editing, variation, upscaling or img2img workflows
  • Fixed 1024x1024 output, no aspect-ratio or resolution controls
  • Requires a paid EverArt account and API key; image generation is not free
  • No prompts or resources exposed, so richer agentic patterns need custom code
  • Explicitly not useful for end users — it does not do anything a human would actually want done
  • Feature drift means some primitives (SEP-1686 Tasks, elicitation) may not yet be implemented in every client, producing red herrings during testing
  • Documentation is a single features.md; there is no guided tour that maps each tool to the spec section it exercises
  • TypeScript-only reference — Python or Rust client authors have to translate patterns themselves
  • Sampling and elicitation flows depend on the client honoring them, so a silent client makes it hard to tell whether the server or the client is at fault
Websitegithub.comgithub.com
Pick EverArt MCP Server if
  • ✅ Drop-in MCP server that lets Claude Desktop or VS Code generate images through natural-language tool calls
  • ✅ Exposes five current image models (FLUX 1.1, FLUX 1.1 Ultra, SD 3.5, Recraft Real, Recraft Vector) through a single tool
  • ✅ Tiny TypeScript codebase makes it a useful reference for building your own image-API MCP wrapper
  • ✅ Installs via npx or Docker with a one-click VS Code button, so setup is a few minutes
Pick MCP Everything Server if
  • ✅ Only server that exercises the full MCP feature matrix in one place — tools, resources, prompts, sampling, elicitation, roots, logging, subscriptions, and Tasks
  • ✅ Maintained by the Model Context Protocol project itself, so behavior tracks the spec as it evolves (SEP-1686 Tasks, Streamable HTTP, etc.)
  • ✅ Runs anywhere an MCP client runs — npx, Docker, Claude Desktop, VS Code, Cursor, Windsurf — with stdio or HTTP transports
  • ✅ TypeScript source is short and readable, making it a de-facto reference for how each handler should be shaped