imagemcpserver MCP server

• Addresshttps://mcp.imagemcpserver.com/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on imagemcpserver.com when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

• Stateanswerschecked 2026-10-28
• Tools11
• Server calls itselfimagemcp-mcp-server
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 276 ms.

• Its tools do every use case we checked: remove backgrounds from product photos in one call; convert and compress images for web pages.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score77 of 100answers 100 · does the job 100 · definitions 83 · context 100 · connects 100 · lowered by the warning signs below
• What an agent can do with it2 of 2 use cases
• Answered100% of days7 of 7 daily checks
• Median first answer246 ms
• Space in an agent's context≈ 2,205 tokensthe definitions of all its tools (11), which an agent carries on every turn
• Tool definitionsB · 83 of 100
• Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once

• Not saying whether it only reads or can destroy: 11 of 11

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• get_user_info

  Retrieve profile details of the authenticated ImageMCP user including plan, credits, and account info. Always check user info/credits first before generating or editing images.

• list_models

  List all available OpenRouter image generation models along with provider details, priority score, cost, latency, and supported aspect ratios.

• generate_image

  Generate high-quality AI images using OpenRouter models (Gemini 2.5 Flash, FLUX, Recraft, SDXL, DALL-E 3, etc.). Supports reference images and choice of output format (Cloudflare R2 image URL or base64 data).

• edit_image

  Edit, inpaint, modify, or transform an existing image by supplying an input image (URL or base64), reference images, prompt instructions, and edit action.

• remove_background

  Remove the background from an image completely, isolating the main subject cleanly.

• upscale_image

  Upscale an image to high-resolution 4K quality, enhancing sharpness and fine details using fal-ai/recraft/upscale/crisp.

• text_to_svg

  Synthesize clean, scalable vector SVG code and graphics from text descriptions using fal-ai/recraft/v4.1/text-to-vector.

• compress_image

  Compress and optimize an image file size with quality percentage control and target format output.

• convert_format

  Convert an image file between PNG, JPG/JPEG, WEBP, GIF, TIFF, and AVIF formats. The converted file is re-encoded and returned as a hosted URL. To produce vector SVG artwork use the text_to_svg tool instead — a raster image cannot be…

• generate_transparent_image

  Generate an AI image from a text prompt and automatically convert it into a background-removed transparent PNG cutout using Fal.ai feynobg.

• multicall

  Execute multiple image generation or image processing tool calls concurrently in parallel (e.g. generate multiple images or transparent images at once).