Image recognition MCP servers

A server here analyses or describes what is in an image or video: captions, object detection, visual question answering.

Not here: OCR of documents, generating images and editing images.

236servers
112 remote124 localTagged by Odel's AI, which can make mistakes
By GitHub stars, at most two per publisher
  1. Number 1: Dali by Lulu@lulu-the-narwhal/daliThe prediction MCP — score your prompt before you generate, so you never waste a credit.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.9 GitHub stars.
  2. Number 2: LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text@linkdigest/linkdigestDouyin, Xiaohongshu, TikTok, YouTube, X links to text: transcript, screen text, viral breakdown7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
  3. Number 3: Squish@getsquish/squishGive AI random access to video: timestamped contact sheets + zoom into any start/end range.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.

Best fit

135 made for this, ranked by starsRemoteLocal
  1. AiPayGen — 65+ AI Tools as an MCP Server @damien829/aipaygen65+ AI tools as MCP: research, write, code, scrape, translate, RAG, agent memory, workflows13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
  2. Gemini Image @smithery/artin0123-gemini-image-mcp-serverAnalyze images and videos with Gemini to get fast, reliable visual insights. Handle content from U…8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.2 GitHub stars.
  3. PoloPan Fashion MCP Server @rofoso-com/polopan-fashion-mcpFashion & apparel MCP: visual outfit search, stock verification, and 1-click checkout.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  4. APICK Vision @apick/visionImage/video analysis: NSFW detection, object detection, thumbnails9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  5. SmartTokenGuard @nwjnjjj/smart-token-guardStop burning credits on broken AI video: check every render before you pay for the next one.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
  6. Intelligence Aeternum @codex-curator/intelligence-aeternum-mcpAI training dataset marketplace: 2M+ museum artworks with Golden Codex enrichment7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  7. GemstoneAI @gemstoneaiapp/gemstoneaiAnalyze jewelry photos, see comparable listings and sales, and save the piece to a collection.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  8. Perception @geiant/mcp-perceptionGeospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. Mapillary @pipeworx-io/mapillaryMapillary MCP — wraps the Mapillary Graph API (graph.mapillary.com)6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  10. TeamAgent @aicare/aicare-mcpAIcare 康护评估 MCP:7 个工具、22 类检测(13 类 live)。输出健康评估与康护建议,非医学诊断。9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  11. AgentPay — Pay-per-call AI Microservices @agentpay/agentpay34 pay-per-call AI microservices via x402, USDC on Base, no API keys.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  12. VidWords YouTube @vidwords/youtubeExtract YouTube transcripts, search what was said, and read on-screen frames with cited timestamps.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  13. Andreax @moralito311-andr/andreax270 pay-per-call AI tools for agents, paid via x402 (USDC on Base). No signup, no API keys.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  14. Primate Intelligence MCP @primateintelligence/mcpVideo scene understanding for AI agents via the Primate Vision API.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  15. Blixtworks @blixtworks/tools63 pay-per-call tools for agents: vision, text, data, web, blockchain. USDC on Base via x402.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  16. FrameFetch @marvinrey7879/framefetchAny social-video URL → transcript, metadata, frames, OCR, summary, search, Q&A. MCP server + x402.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  17. GroundTruth — subsurface scan QA & trade estimating @gtfi/groundtruthTwo independent AI models read a GPR, locate or pipe scan and flag the do-not-core call.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  18. ARPI MCP @arpi/arpi-mcpAI-powered ECG analysis: submit ECG images and receive diagnosis reports from ARPI's ECG AI.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  19. Picdefenseio @rchanllc/picdefenseio-mcp-serverImage risk scoring, EXIF, reverse-image backlinks, and image content detection via PicDefense.io.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  20. Social → Context @mcp-dir/socialdl-mcpTurn a TikTok/Instagram/YouTube link into text for your AI: metadata, transcript and image OCR.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  21. Kultur.dev @kultur-dev/kultur-devCultural Intelligence Infrastructure for AI Agents — 200+ markets, 15 tones, 8 tools8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.

Also touches on Image recognition

45 where it is one part of a bigger job