T
traeai
Sign in

概念

Model Context Protocol

别名:MCP

一种用于连接 AI 代理与数据源的标准协议。

已跟踪 9 条高相关材料

TraeAI 观察

相关材料

已收录 9 条与 Model Context Protocol 相关的内容,按评分排序。

AI-assisted testing, extensions updates, and more: k6 2.0 is here

AI-assisted testing, extensions updates, and more: k6 2.0 is here

Grafana Labs1683 字 (约 7 分钟)
90

k6 2.0 released with AI-assisted testing workflows, introducing 4 new CLI commands for deep integration with AI tools like Claude Code, boosting test automation efficiency by over 50%.

入选理由:k6 2.0新增k6 x agent命令,使AI助手能自动生成符合k6规范的测试脚本,减少人工编写时间50%+。

FeaturedArticle#k6#performance testing#AI-assisted#CI/CD英文
Connecting AI agents with unstructured data using Google Cloud Storage MCP Servers

This article explores how to connect AI agents with unstructured data using Google Cloud Storage (GCS) MCP servers, providing three customer case studies and detailing how GCS's two MCP server options simplify agent deployment.

入选理由:Palo Alto Networks 的 Strata Co-Pilot 使用 GCS MCP 服务器作为其‘历史记忆’,结合 Gemini Live API 提供屏幕感知的网络配置辅助。

FeaturedArticle#Google Cloud#AI Agents#GCS#MCP#Unstructured Data英文
Hacker News Best 图标

Reasonix — DeepSeek-native AI Coding Agent

Hacker News Best1267 字 (约 6 分钟)
85

Reasonix is a terminal-native AI coding assistant designed for DeepSeek API, achieving up to 94% cache hit rate and 2.5x cost reduction via byte-stable caching.

入选理由:Reasonix 使用 DeepSeek 的 prefix cache 机制,实现 94% 缓存命中率和 1/5 输入 token 成本

FeaturedArticle#AI Agent#Terminal#DeepSeek#Caching#LLM英文
Meet the latest Database Center, now with Gemini-powered fleet intelligence

Database Center Improvements from Next ‘26

Google Cloud Blog925 字 (约 4 分钟)
85

Google Cloud introduces Gemini-powered Database Center for enhanced database management.

入选理由:Gemini 提供舰队级智能分析,从被动响应转为主动 AI 分析。

FeaturedArticle#Google Cloud#Database Management#AI#Gemini英文
Google I/O 2026: The Agent Layer Takes Shape

Google I/O 2026: The Agent Layer Takes Shape

Gradient Flow3431 字 (约 14 分钟)
82

Google I/O 2026 announced AI agent layer as core strategy, shifting AI from Q&A tool to workflow executor via products like Gemini Spark.

入选理由:Gemini Spark是7*24小时运行的持久性AI代理,将集成Chrome、Workspace和Android平台

FeaturedArticle#Google#AI Agents#I/O Conference#Artificial Intelligence#Search英文
Extending conversational memory in Kiro CLI using Amazon Bedrock AgentCore Memory

Extending conversational memory in Kiro CLI using Amazon Bedrock AgentCore Memory

AWS Machine Learning Blog1500 字 (约 6 分钟)
82

By building a custom MCP server integrated with Amazon Bedrock AgentCore Memory, Kiro CLI achieves persistent conversational memory across sessions, solving the context forgetting issue in Agentic IDEs.

入选理由:利用 MCP 协议将 Bedrock AgentCore Memory 集成到 Kiro CLI,实现跨会话记忆。

FeaturedArticle#AWS#MCP#Agent#Kiro CLI#Bedrock英文
A Smarter Google AI Edge Gallery: MCP integration, notifications, and session continuity

A Smarter Google AI Edge Gallery: MCP integration, notifications, and session continuity

Google Developers Blog1169 字 (约 5 分钟)
80

Google AI Edge Gallery introduces three major capabilities: MCP protocol support for cross-data-source tool calling, local notification scheduling for proactive interactions, and persistent chat history, shifting mobile Agent development from reactive to automated and continuous experiences.

入选理由:通过注册MCP URL,应用可将工具定义动态导入本地模型系统提示词,推理完全在手机端完成,请求由MCP服务器执行

FeaturedArticle#Google AI Edge Gallery#MCP#On-device AI#Gemma 4#Mobile Agent英文
The future of agentic development: Redefining the data practitioner lifecycle with Data Agent Kit

Data Agent Kit brings data skills and tools to your IDE or CLI

Google Cloud Blog1649 字 (约 7 分钟)
80

Google Cloud's Data Agent Kit is an open-source toolkit integrating BigQuery and other platforms into IDEs or CLIs via MCP, enabling intent-driven data engineering with pre-built skills to solve context window limits and fragmentation.

入选理由:Data Agent Kit 通过 MCP 工具提供 VS Code、Claude Code 等 IDE 与 BigQuery、AlloyDB 的安全连接。

FeaturedArticle#Google Cloud#Data Agent Kit#MCP#BigQuery#AI Agents英文
Scalable voice agent design with Amazon Nova Sonic: multi-agent, tools, and session segmentation

Scalable voice agent design with Amazon Nova Sonic: multi-agent, tools, and session segmentation

AWS Machine Learning Blog2648 字 (约 11 分钟)
75

AWS proposes three architectural patterns for voice agents—direct tool calling, agent-as-tool delegation, and session segmentation—built on Amazon Nova Sonic, Bedrock AgentCore, and Strands BidiAgent, achieving sub-500ms end-to-end latency while solving multi-agent coordination and real-time audio streaming challenges.

入选理由:AgentCore Gateway 支持 MCP 协议,让 Nova Sonic 直接调用工具,消除中间推理层以降低延迟

FeaturedArticle#Voice Agent#Amazon Nova Sonic#Bedrock AgentCore#MCP Protocol#Real-time Audio英文

跨材料问答 · Model Context Protocol

回答基于:Model Context Protocol 相关 9 条材料
    0 / 500

    AI may generate inaccurate information. Please verify important content.