TV shows - 梅斯AI导航站

MCP-ADB

MCP (Model Context Protocol) Server to control Android TV

Gmail MCP Server

This repo shows how Gmail account can be connect to LLMs using MCP

GPTDARR - Sonarr & Radarr MCP Server

A MCP Server for efficiently managing and automating TV shows and movies in Sonarr and Radarr setups. Simplify your media library management with AI-driven insights and commands.

Frankraitv_mcp2.0 Server

Mirror of

MCP_sertver-algorithm

알고리즘 MCP를 구현해보자

MCP Service

bgm.tv MCP Server

MCP Geocoder Rosetta

A "rosetta stone" repo that shows creating simple geocoder MCP servers in python (with googlemaps sdk and direct googlemaps API with urllib) and typescript. CLI clients and documentation on adding the

MCP with RAG Demo

This demonstration project shows how to implement a Model Context Protocol (MCP) server with Retrieval-Augmented Generation (RAG) capabilities. The demo allows AI models to interact with a knowledge b

Solana-MCP-Trading-Server

server that shows trending tokens and integrates Grok, xAI image understanding and vision (interpreted as a vision-capable AI), and Claude's computer use capabilities.

Command Injection Vulnerability in MCP File Reader

A deliberately vulnerable MCP server demonstrating command injection flaws. This Python implementation shows how lack of input sanitization in file paths leads to critical security vulnerabilities all

CCTV VMS MCP

A Model Context Protocol (MCP) server designed to connect to a CCTV recording program (VMS) to retrieve recorded and live video streams. It also provides tools to control the VMS software, such as sho

FastVLM

苹果 FastVLM 的模型让你的 iPhone 瞬间拥有了“火眼金睛”，不仅能看懂图片里的各种复杂信息，还能像个段子手一样跟你“贫嘴”!而且最厉害的是，它速度快到飞起，苹果官方宣称，首次给你“贫嘴”的速度比之前的一些模型快了足足85倍!这简直是要逆天啊! 视觉语言模型的 “成长烦恼” 现在的视觉语

RelightVid

RelightVid是上海 AI Lab、复旦大学、上海交通大学、浙江大学、斯坦福大学和香港中文大学推出用在视频重照明的时序一致性扩散模型，支持根据文本提示、背景视频或HDR环境贴图对输入视频进行细粒度和一致的场景编辑，支持全场景重照明和前景保留重照明。模型基于自定义的增强管道生成高质量的视频重照明数据对，结合真实视频和3D渲染数据，在预训练的图像照明编辑扩散框架（IC-Light）基础上，插入可

ROMA——平替Deep Research

ROMA是一个元代理框架，它使用递归分层结构来解决复杂问题。通过将任务分解为可并行执行的组件，ROMA 使代理能够应对复杂的推理挑战，同时保持透明性，从而简化上下文工程和迭代。该框架提供并行问题解决功能，代理可以同时处理复杂任务的不同部分；其开发过程透明，结构清晰，易于调试；此外，我们搜索代理的强大基准测试结果也证明了其卓越的性能。我们已经展示了该框架的有效性，但这仅仅是个开始。作为一个开源且可扩

PaddleOCR-VL – 百度飞桨开源的多模态文档解析模型

PaddleOCR-VL是百度飞桨团队开源的多模态文档解析模型，参数量仅0.9B，专为低算力设备优化。在国际权威评测OmnidocBench V1.5中以92.6分登顶全球第一，超越GPT-4o等主流模型。模型采用双阶段架构：PP-DocLayoutV2负责版面分析，PaddleOCR-VL-0.9B完成内容识别，支持109种语言，能精准处理表格、公式、图表等复杂元素，输出结构化Markdown/

搜索结果