关键词 "demo walkthrough" 的搜索结果, 共 24 条, 只显示前 480 条
created from MCP server demo
mcp demo for studying mcp, include client and server
Demo of MCP client/server using durable objects for trackings state
A Model Context Protocol server for document Q&A powered by Langflow . It demonstrates core MCP concepts by providing a simple interface to query documents through a Langflow backend.
A demo agent using our MCP server
This project demonstrates how to use Cloudflare Browser Rendering to extract web content for LLM context. It includes experiments with the REST API and Workers Binding API, as well as an MCP server im
A Model Context Protocol server implementation providing mathematical operations through a standardized interface. Built with TypeScript and Node.js, this server demonstrates how to create and expose
A proof-of-concept demonstrating a custom-built host implementing an OpenAI-compatible API with Google Vertex AI, function calling, and interaction with MCP servers.
Use Model Context Protocol with multiple Fireproof JSON document databases
An exploration of common MCP server vulnerabilities, along with a deep dive into MCP server prompt injection (+demonstrations for each!).
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
This repository demonstrates a security vulnerability in MCP (Model Context Protocol ) servers that allows for remote code execution and data exfiltration through tool poisoning.
🔒 Reference MCP servers that demo how authentication works with the current Model Context Protocol spec.
MCP server for PowerPoint
This is a TypeScript-based Model Context Protocol (MCP) server that implements a virtual pet simulation system. It demonstrates core MCP concepts by providing tools for pet care and interaction.
RWKV开源发布了 RWKV7-G1 1.5B 推理模型(Reasoning Model)。模型基于 World v3.5 数据集训练,包含更多小说、网页、数学、代码和 reasoning 数据,总数据为 5.16T tokens。其具备其它同尺寸模型不具备的推理能力和任务能力,同时还支持现实世界 100+ 种语言。 在实际测试中,RWKV7-G1 1.5B 模型的推理逻辑性较强,能够完成有难度的
Step1X-3D是什么 Step1X-3D 是StepFun联合LightIllusions推出的高保真、可控的 3D 资产生成框架。基于严格的数据整理流程,从超过 500 万个 3D 资产中筛选出 200 万个高质量数据,创建标准化的几何和纹理属性数据集。Step1X-3D 支持多模态条件输入,如文本和语义标签,基于低秩自适应(LoRA)微调实现灵活的几何控制。Step1X-3D 推动了 3
DreamFit是什么 DreamFit是字节跳动团队联合清华大学深圳国际研究生院、中山大学深圳校区推出的虚拟试衣框架,专门用在轻量级服装为中心的人类图像生成。框架能显著减少模型复杂度和训练成本,基于优化文本提示和特征融合,提高生成图像的质量和一致性。DreamFit能泛化到各种服装、风格和提示指令,生成高质量的人物图像。DreamFit支持与社区控制插件的无缝集成,降低使用门槛。 Dre
WorldMem 是南洋理工大学、北京大学和上海 AI Lab 推出的创新 AI 世界生成模型。模型基于引入记忆机制,解决传统世界生成模型在长时序下缺乏一致性的关键问题。在WorldMem中,智能体在多样化场景中自由探索,生成的世界在视角和位置变化后能保持几何一致性。WorldMem 支持时间一致性建模,模拟动态变化(如物体对环境的影响)。模型在 Minecraft 数据集上进行大规模训练,在真实
ZenCtrl 是 Fotographer AI 推出的 AI 图像生成工具,支持从单张图像生成高质量、多视角和多样化场景的图像,无需额外训练数据。基于先进算法和图像处理技术,支持实时元素再生,适用于产品摄影、虚拟试穿、人物肖像控制、插画等场景。ZenCtrl 为创意和商业领域中高效、灵活的视觉内容生成解决方案。 ZenCtrl的主要功能 多视角和多样化场景生成:从单张主题图像生成高质量、
只显示前20页数据,更多请搜索
Showing 313 to 336 of 344 results