Image Understanding

MCP server (FastMCP) exposing ROS 2 image topics to VLM agents

Every smart contract deserves intelligence, not just data. On-chain indicators via Chainlink.

PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.

基于智谱AI拍照解题智能体的STDIO类型MCP服务

Structured visual analysis pipeline for coding agents - give your AI agent the ability to see

OCI Vision MCP server

MCP server for camera/vision tools - connect any camera to AI assistants

Compress OCR-heavy PDFs into dense packed images so agents can work with long visual documents.

为纯文本大模型提供视觉能力的 MCP Server：读图 · 识字 · 解表格 · 复刻 UI。Give text-only LLMs vision via MCP: image description, OCR, VQA, UI layout & tables.

MCP server providing OpenCV computer vision capabilities

MCP server with image tools (vision + processing) supporting multiple providers

Local-first document MCP for AI agents: create, read, secure and sign PDF/Word/Excel/PPTX.

AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs.

MCP server for remote control of napari viewers via Model Context Protocol

FastMCP server for Moondream vision language model

FastMCP server for Moondream vision language model

MCP server for visual understanding via Xiaomi MIMO multimodal API

MCP server for MIMO image recognition

MCP server that delegates vision tasks to a configurable vision model

An MCP server providing zero-shot object detection and segmentation using Ultralytics YOLOE.