MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP服务器用于图片识别和信息提取
npm MIT -
image-recognition-mcpgithub.com/akirose/image-recognition-mcpupdated this year
—
MIT ★ 7 -
—
npm ★ 5 -
mcp for ocr and image recognition
-
MCP server for MIMO image recognition
pypi -
OpenAI-compatible vision recognition MCP server for Claude Code (and any MCP client).
npm MIT -
MCP server for image recognition using vision APIs (Anthropic, OpenAI, Cloudflare Workers AI)
pypi MIT -
An MCP server that provides image recognition 👀 capabilities using Anthropic and OpenAI vision APIs
MIT ★ 40 -
@iflow-mcp/mario-andreschak-mcp-video-recognitionupdated this year
MCP server for Google Gemini image, audio, and video recognition
npm MIT -
MCP tool for multimodal image recognition
-
mimo-image-mcpgithub.com/rayner-luo/mimo-image-mcpupdated this year
MCP server for MIMO image recognition
npm MIT -
MCP server for image generation and editing, speech recognition, text recognition, speech synthesis, voice design, video generation and multimodal media analysis.
pypi MIT -
A local MCP server that gives unimodal LLMs multimodal vision — image/video recognition with multi-turn iterative analysis.
npm Apache-2.0 -
CLI and MCP server for LEGO recognition — identify parts, sets, and minifigures from images
npm MIT -
codex-glm-visiongithub.com/Qiu-lin-8/codex-glm-visionupdated this year
GLM-4.6V-Flash free vision MCP server + Codex skill (image recognition / OCR / screenshot analysis)
MIT ★ 1 -
mcp-vision-servergithub.com/coffe-d/mcp-vision-serverupdated this year
MCP server for image recognition via Kimi/Moonshot vision API. Works with Claude Code.
pypi MIT -
vision-mcpgithub.com/weekitmo/vision-mcpupdated this year
MCP server for image understanding through OpenAI-compatible vision APIs. To provide image recognition capabilities for those large models that do not support Multimodal.
MIT -
@iflow-mcp/nazarlysyi-brickscopeupdated this year
CLI and MCP server for LEGO recognition — identify parts, sets, and minifigures from images
npm MIT -
Self-hosted VLM image-recognition MCP server (stdio). Paste an image in Claude Code / Codex / OpenCode → get recognition. OpenAI-compatible backend (vLLM / Ollama / GLM-4V / Qwen-VL).
MIT ★ 1 -
Lightweight OCR MCP Server for AI Models - Privacy-focused image recognition with MCP protocol support
npm MIT -
Standalone MCP server for image recognition via LLM vision API — OCR, image analysis, structured extraction, screenshot-to-accessibility-tree
MIT ★ 1 -
Claude Code 的图像全家桶 MCP——AI 生图/视频 + 图像识别(OCR/表格/图表/VLM)+ 架构图/数据图/分享卡/二维码/公式/嵌套可下钻架构图,21 工具一个装好,纯免费。 | All-in-one image MCP for Claude Code — AI image/video gen + recognition (OCR/table/chart/VLM) + diagrams/charts/cards/QR/formula + nested drill-down architecture. 21 tools, free.
npm MIT ★ 2 -
io.github.shalevshalit/image-recongnition-mcpgithub.com/mcp-s-ai/image-recongnition-mcpno update data
MCP server for AI-powered image recognition and description using OpenAI vision models.
npm -
aiceptiongithub.com/ktmcp-cli/aiceptionupdated this year
CLI for AIception Image Recognition - Kill The MCP
MIT -
ezdxf_mcpgithub.com/crhomagnus/ezdxf_mcpupdated this year
Noncommercial visual web research, image-to-DXF, spatial recognition, and exact Cartesian targeting engine
NOASSERTION -
ocr-mcp-servicegithub.com/qiao-925/ocr-mcp-serviceupdated this year
OCR MCP Service - Image text recognition for AI Agents
★ 1 -
MCP stdio server for image recognition via an existing vision model
npm MIT -
gyy-mcpgithub.com/yourusername/gyy-mcpupdated this year
A FastMCP-based MCP tool with image recognition using Ollama qwen3-vl:8b model
pypi MIT -
This is an unofficial Model Context Protocol (MCP) server that provides various AI capabilities using the DeepInfra OpenAI-compatible API, including image generation, text processing, embeddings, speech recognition, and more.
★ 2 -
@zqt1125/clipboard-vision-mcpgithub.com/zqt1125/clipboard-vision-mcpupdated this year
Clipboard-first MCP server that gives vision-less LLMs image recognition via OpenAI-compatible vision models. Enhanced: primary+backup model failover, TTL result cache, Chinese description output.
npm MIT -
Ui.Vision MCP: MCP server for browser and desktop automation (RPA) with OCR, image recognition and real mouse/keyboard input. Works with Claude Code, Claude Desktop, Codex, Cursor, Windsurf, VS Code, LM Studio and any other MCP client.
npm MIT -
本地视觉理解 MCP 服务,为 AI agent 提供识图能力:通过 vision / ocr / list_models / providers 四个 MCP 工具描述截图、界面、图表与照片。
MIT ★ 5 -
mcp-recognize-imageupdated this year
MCP server that lets text-only models 'see' images via configurable vision LLM providers with priority fallback
pypi MIT -
visual-understand-mcpupdated this year
视觉理解 MCP Server - 为不支持视觉的编码模型提供图片理解能力
pypi -
基于ddddocr的MCP验证码识别服务 - 提供高效准确的图形验证码识别功能
npm MIT -
ForgeSyte is a modular AI‑vision MCP server
★ 1 -
mcp-vision-servergithub.com/joshsssn/mcp-vision-serverupdated this year
MCP server that exposes image analysis tools to LLMs via the Model Context Protocol.
MIT ★ 1 -
image-vision-mcpgithub.com/staticdeng/image-vision-mcpupdated this year
Multi-model vision MCP server (GLM-4.6V, Kimi, Qwen-VL, GPT-4o) that lets text-only coding models in Claude Code see and understand images.
npm MIT -
fast-paddleocr-mcpgithub.com/yourusername/paddleocr-mcpupdated this year
Fast PaddleOCR MCP server - Extract text from images using PaddleOCR with optimized performance
pypi MIT -
xtai-single-mcp-servergithub.com/your-username/xtai-single-mcp-serverupdated this year
Xuantong AI MCP Server - 41 AI tools for shelf recognition, fake photo detection, SKU combination and more
npm MIT -
Vision sidecar MCP server — gives text-only LLMs the ability to see images. Supports OpenAI AND Anthropic API formats.
MIT -
mcp-vision-readactive
识图 MCP server:多模型配置、失败自动降级、agent 可按 tier/model 升级重识
npm MIT -
korgi-vision-ossgithub.com/c0de4un/korgi-vision-ossupdated this year
Open-source, self-hosted platform for distributed image analysis using local Vision LLMs (Moondream 2 / Qwen 2.5). Built with Rust, Axum, and Vue 3.
MIT ★ 1 -
vision-mcp-nodeupdated this year
MCP server: 直连远端多模态模型 API 识别图片/OCR(OpenAI 兼容,如阿里云百炼 qwen3-vl-plus / qwen3.7-plus),不经过本地代理
npm MIT -
wooden-vision-mcpactive
A generic MCP server that lets a text-only LLM agent 'see' images by sending them to any OpenAI-compatible multimodal model (e.g. gpt-4o, glm-4.6v, qwen-vl).
npm MIT -
Self-hosted DeepSeek-OCR-2 WebUI & API — vLLM / transformers on NVIDIA, Apple Silicon & CPU, per-page quality checks, PDF streaming, MCP
MIT ★ 447 -
一本会看照片的饮食日记:拍照识别菜品 → 时间线 / 统计 → 自然语言查询 → 周报 → 健康档案与个性化餐单(含 AI 生图配图)。FastAPI + React + SQLite,多模型、MCP 接入、Android 壳。AI diet diary: snap a meal, get charts, ask in plain language, get weekly reports & AI-illustrated meal plans.
★ 1 -
MCP server providing OCR capabilities to LLMs via Google Cloud Vision API - Read scanned PDFs, handwritten text, and images with any orientation
pypi MIT ★ 1 -
Open-source MCP server for FreezeText — OCR anything on your Mac screen from Claude/Cursor. Screen capture, region OCR, image OCR, searchable history.
MIT ★ 1 -
light-OCR-modulegithub.com/dwain-barnes/light-OCR-moduleupdated this year
Local OCR that turns scanned PDFs and images into clean Markdown — powered by LightOnOCR + llama.cpp. 100% on-device, no cloud, no API keys. Python library, CLI, MCP server, and Claude Code skill in one package
MIT -
OCR in the browser and Node.js with the tesseract.js API: PP-OCRv6-Small on LiteRT.js (WebGPU or WebAssembly), images never leave the device. PDFs, scans and photos to Markdown with tables, JSON or text; a CLI and an MCP server.
npm Apache-2.0