io.github.yichong1/mcp-imgkits

up checked 2026-11-11T03:38:57.283Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

ImgKits MCP

Publisher-provided description

ImgKits MCP: translate, blind watermark, audio, PDF→MD→translate, text utils, colorize.

Summary by lookupd

Translates text, documents, images and subtitles; converts PDFs and images to Markdown; runs OCR, watermarking, colorization, upscaling…

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http imgkits https://mcp.imgkits.com/mcp

Codex, remote (streamable-http)

codex mcp add imgkits --url https://mcp.imgkits.com/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "imgkits": {
      "url": "https://mcp.imgkits.com/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (21 tools)

Publisher-provided text

• convert_to_markdown Convert PDF and image files to clean Markdown for RAG, LLM ingestion, and knowledge bases. Optionally include MinerU layout JSON (content list with blocks and b
• ocr_image Extract text from images, screenshots, and scanned PDF pages. Returns text blocks with block-level bounding boxes [x0, y0, x1, y1] and page indexes. Coordinates
• extract_tables Extract tables from PDFs and images as HTML plus a row/column matrix. Merged cells are expanded; only the top-left cell carries content and other covered cells
• translate_text Translate up to 50,000 characters of plain text (up to 50 strings). Long inputs are split into <=1,900-character chunks automatically. Synchronous. Cost: 1 cred
• translate_document Translate a document from a public URL. Supported formats include PDF, DOCX/DOC, XLSX/XLS, PPTX/PPT, EPUB, TXT, HTML, MD and CSV. Upstream size limits: PDF <= 3
• translate_image Translate text inside 1-10 images supplied as public URLs (JPG/PNG/WebP recommended; keep each image <= 10 MB). This is an async job: the call waits up to wait_
• translate_subtitle Translate SRT, WebVTT or ASS/SSA subtitle content (up to 1,000,000 characters). Timestamps, cue order, SRT/VTT indices and ASS event fields are preserved exactl
• detect_language Detect the language of up to 20,000 characters. Uses a local Unicode-script + stopword/diacritic heuristic; no upstream call. Returns a language code, confidenc
• embed_blind_watermark Embed an invisible/blind watermark into an image supplied as a public URL (JPG/PNG/WebP/BMP, <= 10 MB; at least 64x64 px recommended). Uses the AiController Enc
• decode_blind_watermark Read a blind watermark from an image (public http(s) URL). Uses the AiController CreateDecodeBlindWatermarkTask + GetDecodeBlindWatermarkResult async path. Star
• text_to_sound_effect Generate a short sound-effect WAV from a text prompt via TangoFlux (async create + result poll). Pass `prompt` (<= 2000 chars) with optional `duration` (default
• separate_stems Split a public audio URL into vocals + accompaniment stems via Spleeter 2stems (async create + result poll). Pass `audio_url` (http(s), <= 2048 chars) to start,
• transcribe_audio Transcribe a public audio URL via Faster-Whisper (async create + result poll; no status endpoint). Pass `audio_url` (http(s)) to start or `job_id` to poll. Opti
• generate_subtitles Transcribe a public audio URL with Faster-Whisper and assemble SRT or VTT in the Worker. Pass `audio_url` to start or `job_id` to poll; `format` is `srt` (defau
• text_to_speech Synthesize speech from text via Qwen-TTS using a short `refer_audio` sample (http(s) URL). Pass `text` (<= 5000) + `refer_audio` (+ recommended `refer_audio_tex
• clone_voice_tts Clone a voice from `clone_audio_url` and speak `text` via Qwen-TTS. Requires `authorization_confirmed=true` (own voice or written authorization). Pass `text` +
• pdf_to_markdown_then_translate Convert a public PDF URL to Markdown via MinerU, then translate the markdown via the public text API. Pass `file_url` (or `files` with exactly 1 PDF http(s) URL
• convert_text_style Transform text with a pure in-Worker algorithm (no upstream HTTP). Pass required `text` (≤8000 chars) and `mode` one of: morse, binary, old_english, fancy, uppe
• count_text Count characters, words, lines, and UTF-8 bytes for `text` (≤8000 chars). Latin words + CJK ideographs counted separately; pure algorithm, no upstream. Returns
• colorize_photo Colorize a photo from a public URL. POST {img} to ai.imgkits.com/api/deoldify (AiController Shangse). Black-and-white photos work best; a response with a null U
• upscale_image Upscale an image from a public URL. POST {img, upscale} to ai.imgkits.com/api/restoration. `scale` is 2 (default) or 4 and is sent as `upscale`. Optional `face_

Details

• Version: 1.0.1
• Transports: streamable-http
• Uptime (7 days): 100%
• Median latency: 526 ms
• First indexed: 2026-11-01T14:57:11.506Z
• Last seen in registry: 2026-11-05T06:17:16.619Z
• Repository: https://github.com/yichong1/mcp-imgkits
• Website: https://mcp.imgkits.com

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.yichong1/mcp-imgkits.svg)](https://lookupd.com/servers/io.github.yichong1/mcp-imgkits)

• 62033 servers
• Last crawl: 2026-11-11T15:38:39.561Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp