MCP Server for vision-tools-api

Native macOS OCR and Vision tools for DeepSeek Harness

MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness

Local stdio MCP bridge for zhipu-mcp-proxy vision tools

Vision Tools for YesImBot

NurCLI - fully loaded multi-provider coding agent (TUI, vision, tools, sandbox, skills). One command installs the native binary: npx nur-cli

Universal MCP vision tools (image + video frame understanding). Delegates to any OpenAI-compatible multimodal model, so text-only agents like DeepSeek can "see" via tool calls.

Visual vision tools (describe, OCR, analyze) for opencode as an in-process plugin. Direct fetch to Gemini + NVIDIA NIM with provider-chain fallback, dual-describe, and nested-object config. No MCP server, no subprocess, no pip.

Vision tools (analyze_image, locate_element) for DeepSeek Harness: local ollama, DSH subagent (qwen-vl etc), or OpenAI-compatible HTTP endpoints

An MCP server that provides vision tools to text-only models

MCP server for EastRouter — vision tools that route through your EastRouter API key.

Pi extension: Z.AI GLM-4.6V vision tools — image analysis, OCR, error diagnosis, diagram reading, UI diff, UI-to-code, video analysis

DeepSeek Harness 视觉能力全家桶：vision_understand 工具（OpenAI 兼容视觉 API，默认免费智谱 GLM-4.6V-Flash，限流自动降级 GLM-4V）+ 粘贴/拖拽/按钮三入口识图

Machine-vision nodes for Node-RED on a fixed camera rig: golden-template AOI with position and blemish tolerances, mm/px calibration from a checkerboard, deskew-and-crop of a physical label, caliper edge and line finding over a drawn region, and barcode l

MediaPipe Vision Tasks. See the privacy notice at https://goo.gle/mediapipe-privacy.

MCP server exposing 7 vision tools (analysis, UI→code, OCR, error diagnosis, diagram, data-viz, diff) — works with any Anthropic-Messages-compatible vision model

pi package adding a describe_image tool that lets non-multimodal models delegate image analysis to a vision model

Google Cloud Vision API client for Node.js

Praetor-native vision tools — screen capture (PraetorScreen) + vision analysis primitives. No third-party screenshot lib in the default codepath.

VisionCamera is the fastest and most powerful Camera for react-native.