MCP servers tagged vision

51

keiver/image-tiler-mcp-server

based tile classification.

34

52

Minicpm Vision MCP

为 DeepSeek V4.0 等单模态大模型装上眼睛和耳朵 —— 本地视觉+音频 MCP 服务器，基于 Ollama + MiniCPM-V 4.6 + faster-whisper，图片描述·视频分析·语音转文字

34

53

DS VISION MCP SKILL

DS-VISION V3: auditable visual evidence for coding agents via MCP (visual evidence for agents without native vision).

34

54

Her Eyes

带上她的眼睛 · Give a text-only LLM eyes — a single-binary MCP tool that lets agents like Claude Code / Codex call a vision model to extract structured key information from images.

34

55

Lucida Vision MCP

通用视觉感知 MCP 服务器（眼睛不是大脑）/ General-purpose visual perception MCP server (eyes, not brain)

34

56

Renderly MCP

MCP server for Renderly — clean web screenshots & content for AI agents (vision models, LLMs, RAG).

34

57

OmniParser MCP

MCP server for Microsoft OmniParser: turn screenshots into structured UI elements for GUI agents (such as Claude Desktop / Cursor / Cline)

34

58

Local Vision

Give text-only LLMs (GLM, DeepSeek, ...) eyes. MCP server that reads images and PDFs with a vision model on your own GPU — no API keys, nothing leaves the machine.

34

59

VisionatorMCP

An MCP server for agents that enables models without vision/multimodal support to analyze images using local Ollama vision models.

34

60

Compare MCP

Compare code reviews across models in Claude Code with ranked todos and subagent dispatch via MCP.

34

61

Be My Geminis

Routes every image Claude Code touches through Gemini Vision into typed JSON. Video, MCP, structured visual diff, and a quiet Opus fallback when Gemini's down.

34

62

Mata Kadalz

A local Vision MCP server for any MCP client, using Qwen3-VL through an external llama-server. One secure image-inspection tool over stdio or Streamable HTTP.

34

63

Deepvision Local MCP

本地识图 MCP：给 DeepSeek 等纯文本模型补看图能力（OCR/检测/分割/零样本，全本地）

34

64

Picturereader Zcode

ZCode plugin: pixel-to-text image reading for text-only models. image_scan / image_ocr / image_sample via MCP, plus the image-reading methodology skill. Port of the picturereader…

34

65

Glm4v Vision MCP

GLM-4.6V 图像理解 MCP：识图/OCR/图表解析，原生接入 DeepSeek Harness（dsh-mcp-client），也兼容 Codex/Cline 等

34

66

Dsh Plus

MCP catalog and Vision Bridge for DeepSeek Harness — manage MCP in Settings, caption chat images for text-only models.

34

67

Bridgenode Skill

BridgeNode — x402 pay-per-request AI inference. Agent skill and buyer-side examples for AI agents.

34

68

OpenResponses

Apple-native SwiftUI developer playground for the OpenAI Responses API with streaming, tool calling, computer use, voice, OCR, MCP, and request inspection.

34

69

Vintelaific

vintelaific :night_with_stars::traffic_light::ambulance: : AI Traffic Light # Kaggle Google Capstone Project # Computer Vision # CCTV Camera # Agentic AI

34

70

Bridgenode SDK Python

BridgeNode — x402 pay-per-request AI inference. Python SDK.

34

71

GemmaM5 1 FullStack

Repeatable and auditable local Gemma 4 26B A4B QAT setup for MacBook Air M5 (24 GB) with vision, reasoning, documents, controlled tools, MCP and local APIs. No model weights inclu…

34

72

Fieldvision MCP

MCP servers for precision agriculture computer vision tasks

34

73

Dsh Vision Primitives

Native interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid / zoom / annotate / measure / diff / color / OCR) + MiMo V2.5 multimodal backend…

34

74

Live Course Notes

在电脑上实时旁听直播课，自动生成结构化笔记，并将课程知识蒸馏为可复用的 Agent Skill

34

75

View Image

Model Context Protocol (MCP) server that provides image viewing capabilities for AI agents. Accepts images via file path or base64 data URI and returns them in a standardized mult…

34

76

Codex Glm Vision

Qiu-lin-8

GLM-4.6V-Flash free vision MCP server + Codex skill (image recognition / OCR / screenshot analysis)

34

77

AI Eyes MCP

mcp-tool-shop-org

Grounded visual evaluator MCP server — honest image judgment via SigLIP2 on a pinned model revision. Measures one image-text pair, names the weights that produced the score, and a…

updated a month ago

34

78

My Own Vision MCP

vectorequa

Standalone MCP server for image recognition via LLM vision API — OCR, image analysis, structured extraction, screenshot-to-accessibility-tree

updated 29 days ago

34

79

Visual MCP

Ayi456

An MCP server that gives LLMs without vision the ability to read and understand images.

34

80

Tokenzip

asynx6

Vision models pay for tiles, not megapixels. Per-provider token math, exact + budget resize, zero-dep PNG/JPEG codecs, Claude Code hook, MCP server.

updated a month ago

34

81

Agent Screenshot

rodbland2021

Playwright screenshot tool with Vision-optimised tiling + desktop screen capture for AI agents

34

82

Vision Augment

CaoMeiYouRen

本地优先的多模态视觉 MCP —— 为无视觉 LLM（DeepSeek、GLM 等）提供可自定义端点的看图 / OCR / 文档解析能力。

34

83

Zhipu Vision MCP

apsuadwf

智谱视觉 MCP Server — 为 DeepSeek 等纯文本模型提供免费视觉能力（GLM-4V）

34

84

Vision Kit

Seom-ingit

Make your AI agent a math tutor. Structured extraction of vectors, matrices & geometry from math figures, with dimension-consistency + geometric self-check. Vision plugins for Dee…

34

85

Agent Cam MCP

skr-electronics-lab

Physical camera perception, measurement, and verification tool for MCP AI agents

34

86

Settled Computer

Remote-Skills

Fast computer use for AI agents: event-driven settling MCP server - replaces time.sleep between clicks, waits for the UI to react and stop changing, returns the settled screenshot…

34

87

Lightbox

sameergdogg

Apple Photos for AI tools: a Swift toolkit, CLI and MCP server that index a Photos library on your Mac so Claude and local models can search and look at it.

34

88