[{"data":1,"prerenderedAt":745},["ShallowReactive",2],{"navigation_docs":3,"-ai-mcp-concept":352,"-ai-mcp-concept-surround":740},[4,54,83,116,125,161,179,200],{"title":5,"path":6,"stem":7,"children":8},"Ai","/ai","ai",[9,12,42,46,50],{"title":10,"path":6,"stem":11},"AI 技術探索","ai/index",{"title":13,"path":14,"stem":15,"children":16,"page":41},"Rag","/ai/rag","ai/RAG",[17,21,25,29,33,37],{"title":18,"path":19,"stem":20},"BM25 演算法深入解析：從 TF-IDF 到現代搜尋引擎的核心技術","/ai/rag/bm25-deep-dive-from-tf-idf-to-rag","ai/RAG/bm25-deep-dive-from-tf-idf-to-rag",{"title":22,"path":23,"stem":24},"Dense Retrieval（向量檢索）深入解析","/ai/rag/dense-retrieval-deep-dive","ai/RAG/dense-retrieval-deep-dive",{"title":26,"path":27,"stem":28},"RAG（Retrieval-Augmented Generation）原理與實作入門","/ai/rag/rag-intro-principles-and-implementation","ai/RAG/rag-intro-principles-and-implementation",{"title":30,"path":31,"stem":32},"RAG Retrieval Strategy 深入解析","/ai/rag/rag-retrieval-strategy-deep-dive","ai/RAG/rag-retrieval-strategy-deep-dive",{"title":34,"path":35,"stem":36},"Reciprocal Rank Fusion（RRF）教學：打造更穩定的檢索融合策略","/ai/rag/rrf-reciprocal-rank-fusion-guide","ai/RAG/rrf-reciprocal-rank-fusion-guide",{"title":38,"path":39,"stem":40},"TF-IDF（Term Frequency–Inverse Document Frequency）深入解析","/ai/rag/tf-idf-deep-dive","ai/RAG/tf-idf-deep-dive",false,{"title":43,"path":44,"stem":45},"Docus AI 功能完整實作指南","/ai/docus-ai-implementation","ai/docus-ai-implementation",{"title":47,"path":48,"stem":49},"llms.txt 是什麼？在 Nuxt 中控制 AI 與搜尋引擎爬蟲的新方式","/ai/llms-txt","ai/llms-txt",{"title":51,"path":52,"stem":53},"MCP（Model Context Protocol）是什麼？用「AI 的 USB-C」理解模型如何安全連接工具與資料","/ai/mcp_concept","ai/mcp_concept",{"title":55,"path":56,"stem":57,"children":58,"page":41},"Data Analysis","/data-analysis","data-analysis",[59,63,67,71,75,79],{"title":60,"path":61,"stem":62},"Exploratory Data Analysis（EDA）資料探索分析入門","/data-analysis/exploratory-data-analysis-eda","data-analysis/exploratory-data-analysis-eda",{"title":64,"path":65,"stem":66},"PR-AUC 深入解析：不平衡分類問題的重要評估指標","/data-analysis/pr-auc-for-imbalanced-classification","data-analysis/pr-auc-for-imbalanced-classification",{"title":68,"path":69,"stem":70},"ROC-AUC 深入解析：理解分類模型的判斷能力","/data-analysis/roc-auc-complete-guide","data-analysis/roc-auc-complete-guide",{"title":72,"path":73,"stem":74},"SHAP（SHapley Additive exPlanations）模型解釋方法深入解析","/data-analysis/shap-model-interpretation-complete-guide","data-analysis/shap-model-interpretation-complete-guide",{"title":76,"path":77,"stem":78},"Social Network Analysis（SNA）深入解析","/data-analysis/social-network-analysis-sna","data-analysis/social-network-analysis-sna",{"title":80,"path":81,"stem":82},"Time-based Split：為什麼時間序列資料不能使用 Random Split？","/data-analysis/time-based-split-vs-random-split","data-analysis/time-based-split-vs-random-split",{"title":84,"path":85,"stem":86,"children":87,"page":41},"MachineLearning","/machine_learning","machine_learning",[88,92,96,100,104,108,112],{"title":89,"path":90,"stem":91},"Confusion Matrix（混淆矩陣）完整解析","/machine_learning/confusion-matrix","machine_learning/confusion-matrix",{"title":93,"path":94,"stem":95},"Decision Tree 模型完整教學：從原理到 Python 實作","/machine_learning/decision-tree-complete-guide","machine_learning/decision-tree-complete-guide",{"title":97,"path":98,"stem":99},"為什麼 Decision Tree 在 Tabular Data 上常常勝過 Deep Learning？","/machine_learning/decision-tree-vs-deep-learning-on-tabular-data","machine_learning/decision-tree-vs-deep-learning-on-tabular-data",{"title":101,"path":102,"stem":103},"LightGBM 模型入門：理解高效能的 Gradient Boosting 演算法","/machine_learning/lightgbm-intro-for-tabular-data","machine_learning/lightgbm-intro-for-tabular-data",{"title":105,"path":106,"stem":107},"Logistic Regression（Logit 回歸）完整教學","/machine_learning/logistic-regression-complete-guide","machine_learning/logistic-regression-complete-guide",{"title":109,"path":110,"stem":111},"為什麼模型訓練需要 Train / Validation / Test Dataset？","/machine_learning/train-validation-test-dataset","machine_learning/train-validation-test-dataset",{"title":113,"path":114,"stem":115},"XGBoost 原理與實務教學","/machine_learning/xgboost-complete-guide","machine_learning/xgboost-complete-guide",{"title":117,"path":118,"stem":119,"children":120,"page":41},"Network","/network","network",[121],{"title":122,"path":123,"stem":124},"DNS 設定入門：CNAME vs A Record 完整解析","/network/dns-cname-vs-a-record-guide","network/dns-cname-vs-a-record-guide",{"title":126,"path":127,"stem":128,"children":129},"Nuxt","/nuxt","nuxt",[130,133,137,141,145,149,153,157],{"title":131,"path":127,"stem":132},"Nuxt 實戰指南","nuxt/index",{"title":134,"path":135,"stem":136},"Abstraction Layer 與 Adapter 的差別，一次搞懂設計角色","/nuxt/adapter_abstraction_layer","nuxt/adapter_abstraction_layer",{"title":138,"path":139,"stem":140},"Nuxt 4 全面理解 — 專案檔案結構解析","/nuxt/directory_structure","nuxt/directory_structure",{"title":142,"path":143,"stem":144},"Nuxt 前端 build 流程完整解析","/nuxt/frontend_build","nuxt/frontend_build",{"title":146,"path":147,"stem":148},"Nitro 是什麼？從 Nuxt 專案到 Server 與 Edge 的關鍵引擎","/nuxt/nitro","nuxt/nitro",{"title":150,"path":151,"stem":152},"深入理解 Nuxt 的 .nuxt 與 .output：為什麼部署時一定要分清楚？","/nuxt/nuxt_and_output","nuxt/nuxt_and_output",{"title":154,"path":155,"stem":156},"Nuxt 中 dev、build、preview 的差異一次搞懂","/nuxt/nuxt_dev_build_preview","nuxt/nuxt_dev_build_preview",{"title":158,"path":159,"stem":160},"Nuxt Image vs \u003Cimg>：為什麼 Nuxt 3 專案幾乎都該用 \u003CNuxtImg>？","/nuxt/nuxt_image","nuxt/nuxt_image",{"title":162,"path":163,"stem":164,"children":165},"Python 程式開發","/python","python/index",[166,167,171,175],{"title":162,"path":163,"stem":164},{"title":168,"path":169,"stem":170},"如何在 FastAPI 中調用記憶體 Buffer 回傳圖片 (附實例)","/python/memory_buffer","python/memory_buffer",{"title":172,"path":173,"stem":174},"Python 單元測試教學：如何為你的程式撰寫 Test","/python/python-unit-testing-unittest-pytest","python/python-unit-testing-unittest-pytest",{"title":176,"path":177,"stem":178},"如何使用 uv 取代 pip：改善 Python 專案的開發流程","/python/uv","python/uv",{"title":180,"path":181,"stem":182,"children":183,"page":41},"Statistic","/statistic","statistic",[184,188,192,196],{"title":185,"path":186,"stem":187},"卡方檢定（Chi-Square Test）入門教學","/statistic/chi-square-test-intro","statistic/chi-square-test-intro",{"title":189,"path":190,"stem":191},"常見抽樣方法（Sampling Methods）教學：Stratified、Quota、Convenience、Systematic、Simple Random","/statistic/common-sampling-methods-guide","statistic/common-sampling-methods-guide",{"title":193,"path":194,"stem":195},"Cramér’s V 指標介紹：如何衡量兩個類別變數之間的關聯","/statistic/cramers-v-for-categorical-association","statistic/cramers-v-for-categorical-association",{"title":197,"path":198,"stem":199},"Mann–Whitney U 與 Kolmogorov–Smirnov（KS）檢定：非參數統計檢定的入門指南","/statistic/mann-whitney-u-and-ks-test-intro","statistic/mann-whitney-u-and-ks-test-intro",{"title":201,"path":202,"stem":203,"children":204},"WebDev","/web_dev","web_dev",[205,208,234,248,282,312,334],{"title":206,"path":202,"stem":207},"Web 前端開發","web_dev/index",{"title":209,"path":210,"stem":211,"children":212},"瀏覽器與渲染","/web_dev/browser","web_dev/browser/index",[213,214,218,222,226,230],{"title":209,"path":210,"stem":211},{"title":215,"path":216,"stem":217},"瀏覽器儲存空間完整解析：Cookie、localStorage、IndexedDB 到 Cache Storage","/web_dev/browser/browser-storage-comprehensive-guide","web_dev/browser/browser-storage-comprehensive-guide",{"title":219,"path":220,"stem":221},"DOM (Document Object Model) 深入解析","/web_dev/browser/dom","web_dev/browser/dom",{"title":223,"path":224,"stem":225},"Service Worker Request Flow 深入解析","/web_dev/browser/service-worker-request-flow","web_dev/browser/service-worker-request-flow",{"title":227,"path":228,"stem":229},"CSR、SSR 與 SSG 是什麼？前端渲染策略完整比較","/web_dev/browser/ssr_csr_ssg","web_dev/browser/ssr_csr_ssg",{"title":231,"path":232,"stem":233},"Virtual DOM 深入解析：為什麼它能優化前端效能？","/web_dev/browser/virtual_dom","web_dev/browser/virtual_dom",{"title":235,"path":236,"stem":237,"children":238},"圖形技術","/web_dev/graphics","web_dev/graphics/index",[239,240,244],{"title":235,"path":236,"stem":237},{"title":241,"path":242,"stem":243},"為什麼 Three.js 專案幾乎都選擇 CSR？從 SSR 問題談起","/web_dev/graphics/threejs_csr","web_dev/graphics/threejs_csr",{"title":245,"path":246,"stem":247},"WebGL 是什麼？為什麼前端 3D 幾乎都靠它？","/web_dev/graphics/webgl","web_dev/graphics/webGL",{"title":249,"path":250,"stem":251,"children":252},"架構與配置","/web_dev/infrastructure","web_dev/infrastructure/index",[253,254,258,262,266,270,274,278],{"title":249,"path":250,"stem":251},{"title":255,"path":256,"stem":257},"Zeabur + K3s + Nuxt 部署架構完整解析","/web_dev/infrastructure/k3s-zeabur","web_dev/infrastructure/K3s-zeabur",{"title":259,"path":260,"stem":261},"ECS vs Docker vs Kubernetes：從部署堆疊理解三層架構","/web_dev/infrastructure/ecs-docker-kubernetes-stack","web_dev/infrastructure/ecs-docker-kubernetes-stack",{"title":263,"path":264,"stem":265},"ECS vs VPS 是什麼？從部署網站的角度一次搞懂差別","/web_dev/infrastructure/ecs-vs-vps","web_dev/infrastructure/ecs-vs-vps",{"title":267,"path":268,"stem":269},"Zeabur 內網服務連線完整入門指南","/web_dev/infrastructure/k3s-internal-networking","web_dev/infrastructure/k3s-internal-networking",{"title":271,"path":272,"stem":273},"使用 Microservices 架構設計系統的優勢解析","/web_dev/infrastructure/microservices-architecture-advantages","web_dev/infrastructure/microservices-architecture-advantages",{"title":275,"path":276,"stem":277},"Nginx 入門教學：從反向代理到與 Kubernetes 的架構比較","/web_dev/infrastructure/nginx-intro","web_dev/infrastructure/nginx-intro",{"title":279,"path":280,"stem":281},"YAML 配置是什麼？為什麼現代開發都在用它","/web_dev/infrastructure/yaml-configuration","web_dev/infrastructure/yaml-configuration",{"title":283,"path":284,"stem":285,"children":286},"網絡與通訊","/web_dev/network","web_dev/network/index",[287,288,292,296,300,304,308],{"title":283,"path":284,"stem":285},{"title":289,"path":290,"stem":291},"HTTP Request 結構完整解析：從 Request Line 到 Header 一次看懂","/web_dev/network/http-request-structure","web_dev/network/http-request-structure",{"title":293,"path":294,"stem":295},"OSI 模型（Open Systems Interconnection Model）完整解析","/web_dev/network/osi-model","web_dev/network/osi-model",{"title":297,"path":298,"stem":299},"RESTful API 設計原則與實務解析","/web_dev/network/restful-api","web_dev/network/restful-api",{"title":301,"path":302,"stem":303},"RESTful API 五大設計原則深入解析","/web_dev/network/restful-api-principles","web_dev/network/restful-api-principles",{"title":305,"path":306,"stem":307},"Server-Sent Events (SSE) 深入解析與實作教學","/web_dev/network/sse-introduction","web_dev/network/sse-introduction",{"title":309,"path":310,"stem":311},"WebSocket 入門教學：從概念到 Node.js 實作","/web_dev/network/websocket-introduction","web_dev/network/websocket-introduction",{"title":313,"path":314,"stem":315,"children":316},"認證與安全","/web_dev/security","web_dev/security/index",[317,318,322,326,330],{"title":313,"path":314,"stem":315},{"title":319,"path":320,"stem":321},"使用 Cookie 與 Session 建立使用者驗證（完整新手教學）","/web_dev/security/cookie-session-authentication","web_dev/security/cookie-session-authentication",{"title":323,"path":324,"stem":325},"JWT 驗證機制完整解析：從登入流程到實務應用","/web_dev/security/jwt-authentication","web_dev/security/jwt-authentication",{"title":327,"path":328,"stem":329},"Secret Key 簽名是什麼？從零理解資料簽名的本質","/web_dev/security/secret-key-signing","web_dev/security/secret-key-signing",{"title":331,"path":332,"stem":333},"SSH（Secure Shell）是什麼？從遠端登入到安全通道的核心概念","/web_dev/security/ssh","web_dev/security/ssh",{"title":335,"path":336,"stem":337,"children":338},"SEO 與規範","/web_dev/seo","web_dev/seo/index",[339,340,344,348],{"title":335,"path":336,"stem":337},{"title":341,"path":342,"stem":343},"Canonical URL 是什麼？用生活化方式搞懂前端 SEO 的基本保命符","/web_dev/seo/canonical_link","web_dev/seo/canonical_link",{"title":345,"path":346,"stem":347},"robots.txt 是什麼？SEO 的第一道守門員","/web_dev/seo/robot_txt","web_dev/seo/robot_txt",{"title":349,"path":350,"stem":351},"Nuxt SEO 中的 Meta 與 SEO 工具是如何運作的？","/web_dev/seo/seo","web_dev/seo/seo",{"id":353,"title":51,"body":354,"description":726,"extension":727,"links":728,"meta":729,"navigation":737,"path":52,"seo":738,"stem":53,"__hash__":739},"docs/ai/mcp_concept.md",{"type":355,"value":356,"toc":713},"minimark",[357,362,379,386,399,404,416,420,436,440,443,464,473,479,488,492,503,510,514,517,543,550,554,564,572,576,579,586,593,600,604,614,622,625,628,640,649,660,671,682,693,702],[358,359,361],"h1",{"id":360},"mcp-是甚麼","MCP 是甚麼?",[363,364,365,366,370,371,375,376],"p",{},"當你希望 AI 不只「回答問題」，而是能",[367,368,369],"strong",{},"讀檔、查資料庫、呼叫內部 API、操作開發工具","時，最常見的痛點是：每接一個工具就要做一套客製整合，長期會變成「模型 × 工具」的爆炸式組合（N×M）難以維護。MCP（Model Context Protocol）要解決的，就是把這件事標準化：用一個通用協議，讓 AI 應用能以一致方式連接外部工具與資料來源。這也是官方常用的比喻——把 MCP 想成「AI 的 USB-C 連接埠」。",[372,373,374],"span",{},"1"," ",[372,377,378],{},"5",[363,380,381],{},[382,383],"img",{"alt":384,"src":385},"MCP USB-C","./mcp/USB_analog.png",[363,387,388],{},[389,390,391,392],"em",{},"Source: ",[393,394,398],"a",{"href":395,"rel":396},"https://pub.towardsai.net/mcp-the-flip-side-of-the-usb-c-analogy-af98e07bdb30",[397],"nofollow","MCP: The Flip Side of the USB-C Analogy | by Peilun Li | Towards ",[400,401,403],"h2",{"id":402},"一mcp-的核心概念把上下文與能力變成可插拔的服務","一、MCP 的核心概念：把「上下文與能力」變成可插拔的服務",[363,405,406,407,410,411,375,413],{},"MCP 是一個開放標準／開放規格，用來定義 ",[367,408,409],{},"LLM 應用（Client/Host）如何與外部系統（Server）交換上下文（context）與呼叫工具（tools）","。你可以把它理解成：AI 端只需要學會「講 MCP」，就能用同一種方式去連不同的資源（檔案、DB、SaaS、內網服務）。這讓工具整合不再綁定特定模型或單一平台，而是更接近「可插拔、可替換」的基礎設施。",[372,412,374],{},[372,414,415],{},"2",[400,417,419],{"id":418},"二為什麼-mcp-會變重要從寫死的工具函式走向可擴展的-agent-生態","二、為什麼 MCP 會變重要：從「寫死的工具函式」走向「可擴展的 Agent 生態」",[363,421,422,423,426,427,430,431,375,433],{},"過去你可能用過 function calling、plugins、各家 SDK 的 tool schema，但通常仍是",[367,424,425],{},"平台特定","：規格不同、權限模型不同、部署方式不同。MCP 的價值在於把「模型呼叫工具」的互動抽象成一致協議，並以",[367,428,429],{},"Server"," 的型態把工具/資源包裝成可重用的能力。這使得同一個 MCP Server 可以同時提供給不同 AI 應用使用（IDE、Chat App、Agent Workflow），降低重工與維運成本。",[372,432,415],{},[372,434,435],{},"6",[400,437,439],{"id":438},"三mcp-的架構長什麼樣host-client-server","三、MCP 的架構長什麼樣：Host / Client / Server",[363,441,442],{},"MCP 常見的角色分工是：",[444,445,446,453,459],"ul",{},[447,448,449,452],"li",{},[367,450,451],{},"Host","：承載模型的應用（例如桌面版 AI、IDE、內部聊天系統），負責把使用者需求帶進來、顯示結果、管理安全邊界。",[447,454,455,458],{},[367,456,457],{},"Client","：在 Host 內與 MCP Server 對話的元件，負責用 MCP 規格送出請求、接收回應。",[447,460,461,463],{},[367,462,429],{},"：你把「工具、資料、工作流程」封裝成 MCP Server，對外提供標準化介面（例如：讀 Git repo、查 Postgres、打 Jira/Slack、呼叫公司內部服務）。",[363,465,466,467,375,470],{},"整體是一種 client-host-server 的設計，重點是讓 AI 端與外部能力之間有清楚的邊界與會話（session）管理，同時保留安全控管的空間。",[372,468,469],{},"7",[372,471,472],{},"3",[363,474,475],{},[382,476],{"alt":477,"src":478},"MCP architecture","MCP_architecture.png",[363,480,481],{},[389,482,391,483],{},[393,484,487],{"href":485,"rel":486},"https://www.workato.com/the-connector/what-is-mcp/?utm_source=chatgpt.com",[397],"What is MCP? | by Workato",[400,489,491],{"id":490},"四mcp-具體在協議層做了什麼用-json-rpc-定義請求回應","四、MCP 具體在「協議層」做了什麼：用 JSON-RPC 定義請求/回應",[363,493,494,495,498,499,375,501],{},"從協議角度看，MCP 以 ",[367,496,497],{},"JSON-RPC 2.0"," 作為底層訊息格式，讓 client 與 server 之間能用一致的方式送出方法呼叫、參數、回傳值與錯誤處理；並透過規格定義「有哪些能力種類」、「怎麼描述工具」、「怎麼傳資源」等語義層內容。",[372,500,472],{},[372,502,415],{},[363,504,505,506,375,508],{},"這件事的意義是：你不用每次都重新設計一套 API 介面給模型用，而是把工具能力用 MCP 的通用方式掛上去，模型/應用端用同樣的互動模式就能探索並呼叫它。",[372,507,415],{},[372,509,472],{},[400,511,513],{"id":512},"五你會在-mcp-裡遇到的兩個關鍵詞tools-與-resources","五、你會在 MCP 裡遇到的兩個關鍵詞：Tools 與 Resources",[363,515,516],{},"多數 MCP 的實作會把能力分成兩大類：",[444,518,519,537],{},[447,520,521,524,525,529,530,529,533,536],{},[367,522,523],{},"Tools","：可以被呼叫執行的動作（例如：",[526,527,528],"code",{},"searchTickets","、",[526,531,532],{},"createPR",[526,534,535],{},"queryDB","）。",[447,538,539,542],{},[367,540,541],{},"Resources","：可被讀取/瀏覽的上下文資源（例如：檔案、文件、資料表、專案資訊），用來讓模型「拿到足夠上下文」再做推理或呼叫工具。",[363,544,545,546,375,548],{},"這樣的切分很貼近真實需求：AI 要做事通常需要「先取得資訊（resources/context）→ 再執行動作（tools）」的閉環。",[372,547,415],{},[372,549,378],{},[400,551,553],{"id":552},"六安全與風險mcp-不是接上就安全而是把風險變得更可管理","六、安全與風險：MCP 不是「接上就安全」，而是把風險變得更可管理",[363,555,556,557,560,561],{},"MCP 把外部系統接進 AI 的同時，也把風險帶進來：例如",[367,558,559],{},"提示注入（prompt injection）","、惡意/被竄改的 Server、過度授權導致資料外洩等。OpenAI 的 MCP 文件特別提醒：第三方 MCP Server 不由平台背書，應把它視為外部供應鏈，並用最小權限、審核來源、憑證管理與監控稽核來降低風險。",[372,562,563],{},"4",[363,565,566,567,375,569],{},"另外，近期也出現「惡意 MCP Server 套件」被用來悄悄外傳資料的案例報導，凸顯 MCP 生態在成長期更需要建立：來源驗證、版本鎖定、權限分層與行為監控等基本功。",[372,568,563],{},[372,570,571],{},"8",[400,573,575],{"id":574},"七什麼時候你該用-mcp三個很實務的判斷","七、什麼時候你該用 MCP：三個很實務的判斷",[363,577,578],{},"如果你遇到以下情境，MCP 通常值得考慮：",[363,580,581,582,375,584],{},"第一，你的 AI 需要連很多工具/資料，而且來源會持續增加（DB、Git、內部 API、第三方 SaaS），你不想每次都重寫整合。",[372,583,374],{},[372,585,415],{},[363,587,588,589,375,591],{},"第二，你希望工具能力「可重用」：同一套工具同時給 IDE、Chat、Agent workflow 使用，而不是每個產品各做一份。",[372,590,469],{},[372,592,378],{},[363,594,595,596,375,598],{},"第三，你在意安全邊界：希望工具層跟模型層分離、權限與審計清楚，並能逐步擴大能力範圍，而不是一開始就把所有 API 暴露給模型。",[372,597,469],{},[372,599,563],{},[400,601,603],{"id":602},"八小結把-mcp-當成ai-工具整合的底層協議先從可控的小場景開始","八、小結：把 MCP 當成「AI 工具整合的底層協議」，先從可控的小場景開始",[363,605,606,607,612],{},"MCP 的本質不是「讓模型更聰明」，而是讓模型更容易、以更一致的方式取得上下文並安全地執行動作。當你把工具與資料以 MCP Server 封裝起來，你得到的是一種可擴展的整合方式：減少重工、降低耦合、也更利於治理與安全控管。",[393,608,374],{"href":609,"rel":610,"title":611},"https://modelcontextprotocol.io/specification/draft",[397],"Specification (Draft)",[372,613,563],{},[363,615,616,617],{},"如果你準備在自己的專案導入 MCP，建議從「低風險、可觀測、可回滾」的能力開始（例如只讀查詢、文件檢索、Dev 工具輔助），逐步擴到有狀態的寫入操作，會更符合真實團隊的落地節奏。",[393,618,563],{"href":619,"rel":620,"title":621},"https://modelcontextprotocol.io/specification/2025-06-18/architecture",[397],"Architecture (2025-06-18)",[623,624],"hr",{},[400,626,627],{"id":627},"參考資料",[363,629,630,631,636,637],{},"[",[393,632,374],{"href":633,"rel":634,"title":635},"https://www.anthropic.com/news/model-context-protocol",[397],"Introducing the Model Context Protocol","]:\nAnthropic ｜〈Introducing the Model Context Protocol〉\n",[393,638,633],{"href":633,"rel":639},[397],[363,641,630,642,645,646],{},[393,643,415],{"href":609,"rel":644,"title":611},[397],"]:\nModel Context Protocol ｜〈Specification (Draft)〉\n",[393,647,609],{"href":609,"rel":648},[397],[363,650,630,651,656,657],{},[393,652,472],{"href":653,"rel":654,"title":655},"https://modelcontextprotocol.io/docs/learn/architecture",[397],"Architecture overview","]:\nModel Context Protocol ｜〈Architecture overview〉\n",[393,658,653],{"href":653,"rel":659},[397],[363,661,630,662,667,668],{},[393,663,563],{"href":664,"rel":665,"title":666},"https://platform.openai.com/docs/mcp",[397],"Building MCP servers for ChatGPT and API integrations","]:\nOpenAI ｜〈Building MCP servers for ChatGPT and API integrations〉\n",[393,669,664],{"href":664,"rel":670},[397],[363,672,630,673,678,679],{},[393,674,378],{"href":675,"rel":676,"title":677},"https://modelcontextprotocol.io/",[397],"What is the Model Context Protocol (MCP)?","]:\nModel Context Protocol ｜〈What is the Model Context Protocol (MCP)?〉\n",[393,680,675],{"href":675,"rel":681},[397],[363,683,630,684,689,690],{},[393,685,435],{"href":686,"rel":687,"title":688},"https://www.infoq.com/news/2024/12/anthropic-model-context-protocol/",[397],"Anthropic Publishes Model Context Protocol Specification","]:\nInfoQ ｜〈Anthropic Publishes Model Context Protocol Specification〉\n",[393,691,686],{"href":686,"rel":692},[397],[363,694,630,695,698,699],{},[393,696,469],{"href":619,"rel":697,"title":621},[397],"]:\nModel Context Protocol ｜〈Architecture (2025-06-18)〉\n",[393,700,619],{"href":619,"rel":701},[397],[363,703,630,704,709,710],{},[393,705,571],{"href":706,"rel":707,"title":708},"https://www.itpro.com/security/a-malicious-mcp-server-is-silently-stealing-user-emails",[397],"A malicious MCP server is silently stealing user emails","]:\nITPro ｜〈A malicious MCP server is silently stealing user emails〉\n",[393,711,706],{"href":706,"rel":712},[397],{"title":714,"searchDepth":715,"depth":715,"links":716},"",2,[717,718,719,720,721,722,723,724,725],{"id":402,"depth":715,"text":403},{"id":418,"depth":715,"text":419},{"id":438,"depth":715,"text":439},{"id":490,"depth":715,"text":491},{"id":512,"depth":715,"text":513},{"id":552,"depth":715,"text":553},{"id":574,"depth":715,"text":575},{"id":602,"depth":715,"text":603},{"id":627,"depth":715,"text":627},"一篇用實務角度講清楚 MCP 的概念、架構、核心能力與安全注意事項，幫助你快速判斷何時該用 MCP、怎麼開始用。","md",null,{"tags":730,"category":7,"date":736},[731,732,733,734,735],"mcp","ai-agent","llm","tooling","protocol","2026-02-03",true,{"title":51,"description":726},"KKWKNebzsPYLhhqYBkR6XG0zl03nphqJ4tsOo0mOQTs",[741,743],{"title":47,"path":48,"stem":49,"description":742,"children":-1},"認識 llms.txt 的用途與設計理念，了解它如何補足 robots.txt 的不足，並學會在 Nuxt 專案中正確設定與使用。",{"title":60,"path":61,"stem":62,"description":744,"children":-1},"介紹資料科學中 Exploratory Data Analysis（EDA）的核心概念、常見方法與實務流程，幫助理解資料特性並為後續建模做好準備。",1776690840061]