Verifies Cloudflare Turnstile challenges by clicking the checkbox using OpenCV template matching. Supports custom template images for non-English versions.
MIT
458,064 tools. Updated 2026-08-14 20:18
"OpenCV" matching MCP tools:
- Auto-finds and clicks Cloudflare Turnstile checkboxes using a three-tier detection strategy: primary selectors, secondary container search, and optional OpenCV template fallback.MIT
- Solves Cloudflare 'Verify you are human' challenges by automatically locating and clicking the verification checkbox when a page is stuck on the interstitial. Requires opencv-python; otherwise, wait for real page content.MIT
- Probes an RTSP stream or local file to retrieve width, height, and fps, and generates a candidate test case list. Optionally accepts per-frame annotations to include discovered labels.MIT
- Extract text from image files (PNG, JPG, TIFF, BMP) using multiple OCR engines and preprocessing options.MIT
- Check which Python third-party libraries are installed on the device before importing them in scripts. Lists packages available in the AScript App environment.MIT
Matching MCP Servers
- Alicense-qualityFmaintenanceProvides OpenCV computer vision capabilities for AI assistants, enabling image processing, object detection, face detection, and video analysis through natural language.111MIT
- AlicenseAqualityBmaintenanceProvides image and video analysis capabilities for LLMs, with local preprocessing (ffmpeg/OpenCV) and any OpenAI-compatible vision model for understanding and Q&A.4MIT
- Detect and identify multiple objects in an image by cropping each object separately and querying Google Lens for individual identification.MIT
- Locate visual elements on a page using image template matching when DOM selectors are unavailable. Returns coordinates of best match.MIT
- Detect anti-bot walls on the current page and automatically apply the best bypass, including Cloudflare Turnstile verification, returning JSON with detection and bypass results.MIT
- Aligns a smartphone photo of a hand-drawn sketch to a digital map layout, extracts specified ink color, georeferences vectors, and appends polygon or polyline features to an existing geodatabase feature class.Apache 2.0
- Execute Python code to perform any task: HTTP requests, data processing, file operations, system commands, image manipulation, and more with auto-install of needed packages.MIT
- Capture screenshots of the active browser tab with support for full-page stitching, region clipping, and format selection. Options include base64 encoding for vision models and automatic resizing to avoid dimension limits.MIT
- Automatically install Python dependencies for HWP document editing. Choose full install with OCR or lightweight core-only mode.
- Reads a web page and generates two thematically matching images (landscape and portrait) without text or recognizable faces, using a local image generation model.
- Converts native or scanned Korean PDFs into editable HWP/HWPX documents, reconstructing tables, images, and layout for visual similarity.
- Use this when you need to trace features from a reference photo into waypoints. Trace pixel-space features from a reference photo into normalized [0..1] waypoints the agent can map to mm via a known scale anchor and feed to path().spline / path().nurbsSegment. Three backends are dispatched behind the scenes: `opencv` (deterministic; uniform-bg silhouette only), `vision-llm` (Claude vision; named points/cluttered backgrounds; caller-supplied ANTHROPIC_API_KEY), and `hybrid` (opencv silhouette + LLM-labeled named points). Default backend is `auto` — the tool picks based on the image's corner-color stddev. Accuracy honesty: opencv contour is geometrically exact; vision-LLM is typically 5–10% off on dense landmarks. Per-feature `confidence` is reported. Caller pays for any vision-LLM API spend via their own ANTHROPIC_API_KEY. Pair with the `kernelcad-trace-from-image` skill for the conversion-to-mm pipeline.Connector
- AI-grade a trading card image using a 3-stage pipeline: (1) Qwen Vision LLM analyzes corners, edges, surface defects (2) OpenCV measures exact centering ratios programmatically (3) BGS professional capping algorithm adjusts the final grade Returns PSA/Beckett-calibrated subgrades and an overall condition score. Also includes a free ROI verdict (should you grade this card?). PAID: $0.10 per call via x402. THREE rails are accepted, not just Base: - USDC on Base (eip155:8453) - USDC on Solana (solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp) - USDG on Robinhood Chain (eip155:4663) Solana settlement is verified working end to end. (Audit 2026-07-30, BUG-12.) Use this when: a user has a card image and wants to know what grade it would receive from PSA or Beckett.Connector