搜索「Vision」的结果

io.github.putervision/world-model-mcp

Persistent 3D/2D spatial world model for AI agents with dynamic velocity and entity tracking.

io.github.putervision/vision-memory-mcp

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

io.github.putervision/state-memory-mcp

Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.

io.github.putervision/behavior-mcp

In-browser ~60Hz behavior tree execution engine with reactive triggers and blackboard projection.

io.github.putervision/agent-reasoning-mcp

Strategic BDI reasoning engine for autonomous AI agents with spatial utility and replanning.

io.github.visionastro48-dev/aether-machine-relationship-mesh

Machine-native relationship mesh for discovery, help, evidence, and earned trust.

com.globalenvisionproductions/ai-power-grid

持久化的 AI 能力蓄水池：为授权的 AI 工作进行充电、存储、取用与复用。

io.github.putervision/webcrypt

Zero-dependency Web Crypto & AI Agent MCP Server (AES-256-GCM, RSA-4096, PQC, Signatures).

tech.geckovision/surf

把 OpenAPI 规范交给 Gecko，即可得到首次调用就能成功、且屏蔽鉴权细节的智能体工具。

io.github.sologovision/flato-design-mcp

通过托管的 MCP 服务器，把 AI 智能体接入 Flato 的可编辑画布运行时。

io.github.wise-vision/mcp_server_ros_2

通过 MCP 查看 ROS 2 的节点与话题，并调用其服务和动作。

iFlytek 图片理解

io.github.iflytek/iFly-Skills/iflytek-image-understanding

用于用户要求分析图片、描述图像内容或回答与图片相关问题的场景。讯飞图片理解——基于星火视觉（Spark Vision）模型分析图片并回答问题，采用 WebSocket API，仅使用 Python 标准库，无需 pip 依赖。

io.clawhub.quanru/midscene-computer-automation

使用 Midscene 实现基于视觉的桌面自动化，用自然语言控制你的桌面（macOS、Windows、Linux）。

srv-d7aoqmh5pdvs7391dcqg

io.smithery.ciprianpater.srv-d7aoqmh5pdvs7391dcqg

# NWO Robotics MCP Server Control real robots, IoT devices, and autonomous agent swarms through natural language — powered by the [NWO Robotics API](https://nwo.capital). --- ## What This Server Does This MCP server exposes the full NWO Robotics API as 64 ready-to-use tools. Any MCP-compatible AI agent (Claude, ChatGPT, Cursor, etc.) can use it to: - Send natural language instructions to physical robots - Run Visual-Language-Action (VLA) inference on live camera feeds - Plan, validate, and execute multi-step robot tasks - Monitor sensors, detect slip, and fuse multi-modal data - Train robots online with reinforcement learning - Register and manage agent identities on Base mainnet via the Cardiac biometric ID system No local installation needed. The server runs on Render and is ready to connect. --- ## Tools Overview ### 🤖 VLA Inference & Models Run Vision-Language-Action inference on any supported robot. Send a text instruction and camera images, receive joint action vectors in real time. Supports a

io.clawhub.quanru/midscene-android-automation

基于 Midscene 的视觉驱动 Android 设备自动化。完全从截图操作——无需 DOM 或无障碍标签。

io.github.ksgisang/awt

AI 驱动的 E2E 测试 MCP 服务器，通过 DevQA 闭环与 Vision AI 检测并自动修复 UI 缺陷。

io.github.xyun1996/ocular

Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.

ai.primateintelligence/mcp

通过 Primate Vision API 为 AI 智能体提供视频场景理解。

io.github.wuzenghai616-lang/goldbean

51 个百度 AI MCP 工具：OCR、视觉、大模型、语音与 NLP，按次计费，低至 0.001 美元起。

io.github.ARAS-Workspace/claude-kvm

MCP 服务器——通过原生 Swift 守护进程与 Apple Vision OCR，经 VNC 控制远程桌面。

io.github.ArkNill/snapgrab

URL 转截图并附带元数据。Python MCP 服务器，针对 Claude Vision 优化。

io.github.TheSandemon/kaito-query

聚合 Gemini、MiniMax、Replicate、OpenRouter 的 AI LLM 服务。支持视觉、搜索、代码审查。Base 链 USDC 计费。

io.github.prasadabhishek/photographi-mcp

视觉智能指挥中心：面向照片库的本地计算机视觉引擎。

io.clawhub.blueberrywoodsym/x-ai

通过 xAI API 与 Grok 模型对话。支持 Grok-3、Grok-3-mini、视觉模型等。