GLM Vision MCP
Related Servers
Alternatives to GLM Vision MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables image analysis via OpenAI-compatible vision APIs, supporting local files, URLs, and base64 inputs with intelligent tiling for high-resolution images. Provides a secure, configurable MCP stdio server for structured vision analysis.91 npm3MIT
- AlicenseNot gradedqualityAmaintenanceProvides a unified image-understanding tool for AI assistants without native vision, letting them analyze screenshots, error messages, UI layouts, and documents via multiple vision LLM providers. It supports local files, remote URLs, Data URIs, OCR, multi-crop processing, and standard MCP clients.512 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to gain vision capabilities by analyzing images, extracting text, and comparing images through any OpenAI-compatible vision endpoint.24 npmMIT
- AlicenseAqualityBmaintenanceEnables MCP clients to run reverse image searches from image URLs or local files, detect AI-generated images, and check images for NSFW content with confidence scores.328 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides image understanding capabilities via local OCR and cloud VLM, enabling text extraction and visual description through MCP.5 npm2MIT
- FlicenseNot gradedqualityCmaintenanceEnables MCP clients to analyze, inspect, and manipulate images and videos with deterministic FFmpeg/sharp tools and pluggable AI providers, returning timestamped, evidence-backed results that can be independently re-verified.1-
TDQS
Scored across 5 tools
The four analyze_* tools are separated only by input modality (image, images, video, file), and analyze_image vs analyze_images differs only in count, which invites misselection. ocr_image is clearly distinct. Descriptions help somewhat, but an agent could easily pick analyze_images for a single image or analyze_file for an image file.
All tools follow a consistent verb_noun snake_case pattern (analyze_image, analyze_images, analyze_video, analyze_file, ocr_image). The naming is predictable and readable throughout.
Five tools is a reasonable, well-scoped set for a vision analysis server. It is slightly thin—analyze_image and analyze_images could arguably be merged into one tool with a list parameter—but no tool is superfluous.
The surface covers the main modalities: single image, multiple images, video, document, and OCR. Minor gaps remain (no batch OCR, no video-from-local-path handling, no result caching/follow-up operations), but core vision workflows are covered.