Skip to main content
Glama
814,859 tools. Updated 2026-11-21 06:26

"Understanding local computer vision models like YOLO" matching MCP tools:

  • List configured databases with their mode and yolo flag to get the name every other tool needs as its database argument. Reads local connections.json only and opens no connection.
    MIT
  • Discover which AI models are available on your NVIDIA account. Filter by capability code, vision, reasoning, or embedding to find the right model.
    MIT
  • Capture the screen as an image to give vision-capable AI models visual context. Use region, scale, and quality parameters to tailor the capture.
    MIT
  • Run one vision inference on a fresh frame to locate objects or ArUco markers, choosing YOLO, ArUco, or both, and return normalized bounding boxes.
    MIT
  • List xAI API models, local Grok CLI models, and .grok model profiles separately to compare available options.
    MIT
  • List Oracle Cloud Infrastructure AI/ML services including Generative AI, Vision, Speech, Language, and Document Understanding. Filter by service type or model.
    Apache 2.0

Matching MCP Servers

  • A
    license
    B
    quality
    B
    maintenance
    Enables interaction with ESPN Fantasy Football leagues through natural language, allowing users to query rosters, matchups, and injuries, and execute actions via MCP or CLI.
    2
    MIT

Matching MCP Connectors

  • A private persistent computer: files that survive between runs, a bash shell and JavaScript.

  • Earth-observation imagery catalogue from Microsoft's Planetary Computer — search its open…

  • Discover the capabilities, supported models, and limits of the vision-mcp server before using other analysis tools.
    MIT
  • List models available on your API key and identify which ones the server defaults to for image generation and vision tasks.
    MIT
  • Identify objects, text, or anomalies in a local image by specifying a task. Get structured JSON results from AI vision analysis.
    MIT
  • Check if your main model supports native vision to decide whether Atlas Vision tools are needed. Use before analyze_image or ocr_image for text-only models.
    MIT
  • Enables text-only models to understand images: reads text, describes scenes, interprets charts, compares images, and returns results as text.
    MIT
  • Analyze local image files or URLs with Google's Gemini vision models to extract text descriptions or answer questions about screenshots, diagrams, and UI states without loading raw image bytes.
    MIT
  • Understand video content with AI vision: extract key moments, identify objects, people, and activities from local files or URLs.
    Apache 2.0
  • Inspect the vision backend status, covering models, backend type, ffmpeg, speech environment, GPU, and watchdog. Verify readiness and diagnose configuration issues.
    MIT
  • Strip GPS coordinates, camera serial numbers, thumbnail caches, and creator PII from image files to protect privacy before sending them to third-party vision models.
    MIT
  • Render PDF pages as images for vision models; control page ranges, DPI, and output width to send only needed content.
    MIT
  • Send prompts to Google Gemini AI models through a secure CLI interface. Include local files using @path syntax and configure execution modes for safe interactions.
    MIT
  • Install a Blockbench plugin by ID, URL, or local path to enable plugin-specific formats like GeckoLib models.
    MIT