一、开篇:为什么现在要懂 MCP?

初次接触 MCP 服务时,我曾对“手动复制 JSON 配置”的操作感到困惑——更不用说很多平台只提供基础工具,却缺乏配套的资源库和提示模板,这让 MCP 显得既繁琐又“不够好用”。

但今年以来,随着“智能体(Agent)”技术的爆发,AI 调用工具的需求呈指数级增长。变化也随之而来:MCP 服务市场逐渐成型,自动配置功能陆续上线,使用门槛大幅降低;越来越多的 AI 平台宣布支持 MCP 协议,不难看出,MCP 正从“小众技术”走向“规模化应用”的爆发前夜。

不过,目前市面上的 MCP 相关文章却存在明显断层:要么通篇是理论推导和 Python 代码,非技术背景的读者很难跟上;要么只讲“点击哪步、填写什么”的操作流程,却跳过了“为什么要这么做”的核心逻辑,导致读者知其然不知其所以然。

因此,本文会先用通俗的语言和可视化图表,拆解 MCP 的理论基础;再以 ModelScope 的 MCP 市场和 Cherry Studio 客户端为实例,带大家“亲眼看见”MCP 的完整工作过程;最后还会分享实用学习资料和行业观察,帮你真正理解并用好 MCP。

二、先搞懂:MCP 背后的“前序知识”

MCP 并非孤立存在,它与 RAG(检索增强生成)、Function Calling(函数调用)紧密相关——前者解决“AI 缺数据”的问题,后者解决“AI 用工具”的问题,而 MCP 则是在两者基础上,实现了“更标准化、更灵活的工具与数据连接”。所以在讲 MCP 前,我们先快速理清这两个核心概念。

2.1 RAG:给 AI 装上“外部知识库”

RAG(Retrieval Augmented Generation,检索增强生成)的核心作用,是让 AI 不用经过复杂的训练/微调,就能通过“实时调取外部资料”生成更精准的回答。简单说,就是给 AI 配了一个“可随时查阅的知识库”。

img

它的工作流程可以分为“准备阶段”和“使用阶段”两步:

  1. 准备阶段:将需要用到的资料(如文档、报告、数据库内容)通过“嵌入模型(Embedding Model)”转化为计算机能理解的“向量”,再存储到专门的“向量数据库”中;
  2. 使用阶段:当用户提出问题时,系统会先将问题也转化为向量,然后在向量数据库中“搜索”与问题最相似的 N 个资料片段,把这些片段和原问题一起拼成新的提示词,再发给大模型——这样大模型就能结合外部资料,给出更贴合具体场景的回答。

如今 RAG 已经发展出多种进阶形态,比如能自主规划检索步骤的 Agentic RAG、按模块拆分功能的 Modular RAG、基于知识图谱的 Graph RAG 等,不过核心逻辑仍是“检索+生成”的结合。

2.2 Function Calling:让 AI 学会“调用工具”

Function Calling(函数调用)是让大模型“主动使用外部工具”的机制——当 AI 判断仅凭自身能力无法回答问题(比如查实时天气、算复杂数据、调用 API 接口)时,会自动识别需要用到的工具,并触发对应的函数来完成任务。

img
图片来源:ailydoseofds

它的基本工作链路很清晰:

  1. 用户向大模型发送需求(如“查一下北京明天的天气”);
  2. 大模型分析需求后,判断需要调用“天气查询工具”,并生成对应的函数调用指令;
  3. 后端服务接收指令,执行函数调用(对接天气 API 获取数据);
  4. 后端将处理结果(如“北京明天晴,气温 15-25℃”)返回给大模型;
  5. 大模型结合结果,用自然语言整理成最终回答,反馈给用户。

不过 Function Calling 有个明显的局限:不同的工具 API 需要单独封装成不同的函数,而且通常需要编写代码来实现对接——这意味着,一个平台上写好的函数,很难直接复用到另一个平台,灵活性和复用性都比较低。

参考文档:阿里云百炼函数调用指南 https://help.aliyun.com/zh/model-studio/tool-calling-overview/

2.3 终于到 MCP:AI 工具连接的“通用接口”

前面提到,RAG 解决了“数据来源”,Function Calling 解决了“工具调用”,但两者都存在“适配成本高、灵活性不足”的问题——而 MCP 正是为解决这个痛点而生的标准。

MCP(Model Context Protocol,模型上下文协议)是 Anthropic 在 2024 年 11 月 25 日开源的一套开放标准,核心目标是“让 AI 助手能更轻松地连接数据系统、业务工具和开发环境”,最终帮助大模型生成更相关、更精准的响应。

img

如果用生活中的事物类比,MCP 就像是 AI 应用的“USB-C 接口”:过去,不同品牌的设备需要不同的数据线(比如安卓的 Micro-USB、苹果的 Lightning);而 USB-C 统一了标准,一个接口能连接充电头、U盘、显示器等各种外设。MCP 也是如此——它为 AI 模型连接不同数据源(如数据库、文档库)和工具(如计算器、翻译接口)提供了“通用标准”,不用再为每个工具单独适配。

img
图片来源:ailydoseofds

2.3.1 MCP 的核心架构

从技术层面看,MCP 遵循“客户端-服务器”架构,一个“主机应用”可以同时连接多个 MCP 服务器,实现“一站式调用多个工具/数据”的效果。它的核心由三个组件构成:主机(Host)客户端(Client)服务器(Server)

2.3.2 三个组件到底是什么?

我们可以用“人用电脑查资料”的场景来理解这三个组件:

  • 主机(Host):相当于“电脑本身”——它是提供 AI 交互的基础环境,比如 Claude 桌面客户端、代码编辑器 Cursor 等。主机能直接访问工具和数据,并且是 MCP 客户端的“运行载体”;
  • MCP 客户端:相当于“电脑里的浏览器”——它运行在主机内部,负责“传递信息”:一边接收主机的需求,一边与 MCP 服务器通信,是连接主机和服务器的“桥梁”;
  • MCP 服务器:相当于“提供资料的网站/数据库”——它负责暴露具体的功能和数据,主要提供三类服务:
    • 工具服务:让 AI 能通过服务器执行具体操作(如查天气、算数据);
    • 资源服务:向 AI 开放服务器存储的数据(如文档、表格、知识库);
    • 提示服务:提供可重复使用的提示模板或工作流(如“写周报的提示模板”“客户沟通话术模板”)。
2.3.3 MCP 比传统 API 好在哪?

传统 API 的痛点,在于“参数固定、改一点就崩”——而 MCP 用“动态适配”解决了这个问题,我们用“天气查询”的例子对比一下:

对比维度 传统 API MCP 协议
参数处理方式 固定参数,需提前硬编码到代码中 动态获取参数,无需硬编码
功能更新影响 新增参数(如加“温度单位”)后,所有调用者必须修改代码,否则请求失败 服务器更新功能后,会主动告知客户端新参数,客户端自动适配,无需改代码
复用性 不同平台需重新编写适配代码,复用性低 遵循统一标准,一次配置可在多平台复用

具体来看传统 API 的问题:
如果一个天气 API 最初只需要“位置”和“日期”两个参数,开发者会把这两个参数写死在代码里;但如果后来需要新增“温度单位(摄氏度/华氏度)”这个必填参数,API 的“调用规则”就变了——此时所有用这个 API 的开发者都必须修改代码,否则请求会报错或返回错误结果。

img
图片来源:ailydoseofds

而 MCP 的解决思路完全不同:

  1. 当 MCP 客户端(如 Claude)连接服务器(天气服务)时,会先发送一个“询问请求”:“你支持哪些功能?需要什么参数?”;
  2. 服务器会主动返回详细信息,比如“我能查天气,需要位置、日期两个参数”;
  3. 如果后续服务器新增了“温度单位”参数,下一次客户端发起“询问请求”时,服务器会自动把“温度单位”加入功能描述中;
  4. 客户端收到新信息后,会自动调整请求逻辑(比如在交互中让用户选择温度单位),整个过程无需开发者修改代码。

img
图片来源:ailydoseofds

本质上,MCP 是用“中间层”的思想,在 AI 和工具之间加了一个“动态协商”的环节——让 AI 不用提前“死记硬背”工具的调用规则,而是每次使用前主动“问清楚”,从而实现了“工具更新,AI 自动适配”的灵活性。

2.3.4 MCP 的完整工作流程

了解了组件和优势后,我们再看 MCP 是如何“一步步工作”的——整个过程就像“AI 带着客户端,向服务器借工具解决问题”:

img
图片来源:ailydoseofds

  1. 配置阶段:在主机(如 Cherry Studio)上完成 MCP 服务的配置——可以手动输入服务器地址,也可以通过 MCP 市场(如 ModelScope)一键添加;
  2. 需求触发:用户向主机输入问题(如“用公司Q2销售数据做一个趋势图”);
  3. 工具选择:主机内的大模型分析需求后,判断需要调用 MCP 服务器上的“数据可视化工具”,并将选择结果告知 MCP 客户端;
  4. 用户授权:MCP 客户端弹出确认框,询问用户是否允许调用该工具(部分平台支持“自动授权”,可跳过此步);
  5. 请求执行:用户同意后,MCP 客户端向 MCP 服务器发送请求,调用“数据可视化工具”,并传入所需的销售数据;
  6. 结果返回:MCP 服务器执行工具调用,生成趋势图数据,再将结果返回给 MCP 客户端;
  7. 答案整理:MCP 客户端把工具返回的结果和用户的原始问题一起发给大模型,大模型将趋势图数据整理成自然语言描述(如“Q2销售额呈逐月上升趋势,6月达到峰值XX万元”),最终反馈给用户。

看到这里你会发现,RAG、Function Calling 和 MCP 的核心目标其实是一致的——都是通过“借助外部能力”,让大模型突破自身的数据和功能局限,完成更复杂、更贴近实际需求的任务。只不过 MCP 用标准化的协议,把这种“借助外部能力”的过程变得更灵活、更易复用。

三、“看见” MCP 的过程

3.1 ModelScope

img

我们来到魔搭的 MCP 市场:https://modelscope.cn/mcp,这里只是为了演示,其他的 MCP 广场也是一样的。

img

登录以后,我们选择一个 MCP 服务,点击右侧的“连接”按钮,就可以 获取 MCP服务的 SSE URL。

3.2 Cherry Studio

Cherry Studio 官网: https://cherry-ai.com/

img

在右上角点击开启,就可以看到该 MCP 服务提供的工具、提示和资源。

img

可以单独开启和关闭每个可用的工具。

img

每个 MCP 服务手动配置太麻烦,大家也可以点击“同步服务器”,配置 ModelScope 的 API 令牌,配置之后就可以一键同步 ModelScope 上开启的 MCP 服务了。

3.3 开发者模式

img

输入想要问的问题,开启需要的 MCP 服务。

为了看见 MCP 的执行过程,我们还需要通过 Ctrl+Shift+I(Mac端:Command+Option+I)打开开发者模式。

img

第一次请求,发送系统提示词,包括大模型可以选择的工具和要求等,然后给出用户的问题。

img

可以看到第二次调用,模型选择使用 infoq 工具获得资讯后组织语言展示给用户。

index =0 的系统提示词的内容:


{
  "role": "system",
  "content": "In this environment you have access to a set of tools you can use to answer the user's question. You can use one tool per message, and will receive the result of that tool use in the user's response. You use tools step-by-step to accomplish a given task, with each tool use informed by the result of the previous tool use.\n\n## Tool Use Formatting\n\nTool use is formatted using XML-style tags. The tool name is enclosed in opening and closing tags, and each parameter is similarly enclosed within its own set of tags. Here's the structure:\n\n<tool_use>\n  <name>{tool_name}</name>\n  <arguments>{json_arguments}</arguments>\n</tool_use>\n\nThe tool name should be the exact name of the tool you are using, and the arguments should be a JSON object containing the parameters required by that tool. For example:\n<tool_use>\n  <name>python_interpreter</name>\n  <arguments>{\"code\": \"5 + 3 + 1294.678\"}</arguments>\n</tool_use>\n\nThe user will respond with the result of the tool use, which should be formatted as follows:\n\n<tool_use_result>\n  <name>{tool_name}</name>\n  <result>{result}</result>\n</tool_use_result>\n\nThe result should be a string, which can represent a file or any other output type. You can use this result as input for the next action.\nFor example, if the result of the tool use is an image file, you can use it in the next action like this:\n\n<tool_use>\n  <name>image_transformer</name>\n  <arguments>{\"image\": \"image_1.jpg\"}</arguments>\n</tool_use>\n\nAlways adhere to this format for the tool use to ensure proper parsing and execution.\n\n## Tool Use Examples\n\nHere are a few examples using notional tools:\n---\nUser: Generate an image of the oldest person in this document.\n\nAssistant: I can use the document_qa tool to find out who the oldest person is in the document.\n<tool_use>\n  <name>document_qa</name>\n  <arguments>{\"document\": \"document.pdf\", \"question\": \"Who is the oldest person mentioned?\"}</arguments>\n</tool_use>\n\nUser: <tool_use_result>\n  <name>document_qa</name>\n  <result>John Doe, a 55 year old lumberjack living in Newfoundland.</result>\n</tool_use_result>\n\nAssistant: I can use the image_generator tool to create a portrait of John Doe.\n<tool_use>\n  <name>image_generator</name>\n  <arguments>{\"prompt\": \"A portrait of John Doe, a 55-year-old man living in Canada.\"}</arguments>\n</tool_use>\n\nUser: <tool_use_result>\n  <name>image_generator</name>\n  <result>image.png</result>\n</tool_use_result>\n\nAssistant: the image is generated as image.png\n\n---\nUser: \"What is the result of the following operation: 5 + 3 + 1294.678?\"\n\nAssistant: I can use the python_interpreter tool to calculate the result of the operation.\n<tool_use>\n  <name>python_interpreter</name>\n  <arguments>{\"code\": \"5 + 3 + 1294.678\"}</arguments>\n</tool_use>\n\nUser: <tool_use_result>\n  <name>python_interpreter</name>\n  <result>1302.678</result>\n</tool_use_result>\n\nAssistant: The result of the operation is 1302.678.\n\n---\nUser: \"Which city has the highest population , Guangzhou or Shanghai?\"\n\nAssistant: I can use the search tool to find the population of Guangzhou.\n<tool_use>\n  <name>search</name>\n  <arguments>{\"query\": \"Population Guangzhou\"}</arguments>\n</tool_use>\n\nUser: <tool_use_result>\n  <name>search</name>\n  <result>Guangzhou has a population of 15 million inhabitants as of 2021.</result>\n</tool_use_result>\n\nAssistant: I can use the search tool to find the population of Shanghai.\n<tool_use>\n  <name>search</name>\n  <arguments>{\"query\": \"Population Shanghai\"}</arguments>\n</tool_use>\n\nUser: <tool_use_result>\n  <name>search</name>\n  <result>26 million (2019)</result>\n</tool_use_result>\nAssistant: The population of Shanghai is 26 million, while Guangzhou has a population of 15 million. Therefore, Shanghai has the highest population.\n\n\n## Tool Use Available Tools\nAbove example were using notional tools that might not exist for you. You only have access to these tools:\n<tools>\n\n<tool>\n  <name>f_u-LsDUyQWsNFAUjL-_Vi</name>\n  <description>获取 36 氪热榜,提供创业、商业、科技领域的热门资讯,包含投融资动态、新兴产业分析和商业模式创新信息</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"type\":{\"anyOf\":[{\"type\":\"string\",\"const\":\"hot\",\"description\":\"人气榜\"},{\"type\":\"string\",\"const\":\"video\",\"description\":\"视频榜\"},{\"type\":\"string\",\"const\":\"comment\",\"description\":\"热议榜\"},{\"type\":\"string\",\"const\":\"collect\",\"description\":\"收藏榜\"}],\"default\":\"hot\",\"description\":\"分类\"}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fyQ3DOUpLJDGPLCjslT6P1</name>\n  <description>获取 9to5Mac 苹果相关新闻,包含苹果产品发布、iOS 更新、Mac 硬件、应用推荐及苹果公司动态的英文资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fBOukVLVbqIh69earzcYca</name>\n  <description>获取 BBC 新闻,提供全球新闻、英国新闻、商业、政治、健康、教育、科技、娱乐等资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"category\":{\"anyOf\":[{\"type\":\"string\",\"const\":\"\",\"description\":\"热门新闻\"},{\"type\":\"string\",\"const\":\"world\",\"description\":\"国际\"},{\"type\":\"string\",\"const\":\"uk\",\"description\":\"英国\"},{\"type\":\"string\",\"const\":\"business\",\"description\":\"商业\"},{\"type\":\"string\",\"const\":\"politics\",\"description\":\"政治\"},{\"type\":\"string\",\"const\":\"health\",\"description\":\"健康\"},{\"type\":\"string\",\"const\":\"education\",\"description\":\"教育\"},{\"type\":\"string\",\"const\":\"science_and_environment\",\"description\":\"科学与环境\"},{\"type\":\"string\",\"const\":\"technology\",\"description\":\"科技\"},{\"type\":\"string\",\"const\":\"entertainment_and_arts\",\"description\":\"娱乐与艺术\"}],\"default\":\"\"},\"edition\":{\"anyOf\":[{\"type\":\"string\",\"const\":\"\"},{\"type\":\"string\",\"const\":\"uk\",\"description\":\"UK\"},{\"type\":\"string\",\"const\":\"us\",\"description\":\"US & Canada\"},{\"type\":\"string\",\"const\":\"int\",\"description\":\"Rest of the world\"}],\"default\":\"\",\"description\":\"版本,仅对 `category` 为空有效\"}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fTU2iCLtmsEWljy_HbEhCa</name>\n  <description>获取哔哩哔哩视频排行榜,包含全站、动画、音乐、游戏等多个分区的热门视频,反映当下年轻人的内容消费趋势</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"type\":{\"anyOf\":[{\"type\":\"number\",\"const\":0,\"description\":\"全站\"},{\"type\":\"number\",\"const\":1,\"description\":\"动画\"},{\"type\":\"number\",\"const\":3,\"description\":\"音乐\"},{\"type\":\"number\",\"const\":4,\"description\":\"游戏\"},{\"type\":\"number\",\"const\":5,\"description\":\"娱乐\"},{\"type\":\"number\",\"const\":188,\"description\":\"科技\"},{\"type\":\"number\",\"const\":119,\"description\":\"鬼畜\"},{\"type\":\"number\",\"const\":129,\"description\":\"舞蹈\"},{\"type\":\"number\",\"const\":155,\"description\":\"时尚\"},{\"type\":\"number\",\"const\":160,\"description\":\"生活\"},{\"type\":\"number\",\"const\":168,\"description\":\"国创相关\"},{\"type\":\"number\",\"const\":181,\"description\":\"影视\"}],\"default\":0,\"description\":\"排行榜分区\"}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>f_OULD1Qnu5wPblKHFTzYw</name>\n  <description>获取豆瓣实时热门榜单,提供当前热门的图书、电影、电视剧、综艺等作品信息,包含评分和热度数据</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"type\":{\"anyOf\":[{\"type\":\"string\",\"const\":\"subject\",\"description\":\"图书、电影、电视剧、综艺等\"},{\"type\":\"string\",\"const\":\"movie\",\"description\":\"电影\"},{\"type\":\"string\",\"const\":\"tv\",\"description\":\"电视剧\"}],\"default\":\"subject\"},\"start\":{\"type\":\"integer\",\"default\":0},\"count\":{\"type\":\"integer\",\"default\":10}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fL5c-CwZ3bUckaatY_MC8Z</name>\n  <description>获取抖音热搜榜单,展示当下最热门的社会话题、娱乐事件、网络热点和流行趋势</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>flPxhdB8Wyw8DDuban0pMa</name>\n  <description>获取机核网游戏相关资讯,包含电子游戏评测、玩家文化、游戏开发和游戏周边产品的深度内容</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fdj1bDLATGns6ZdclA68UF</name>\n  <description>获取爱范儿科技快讯,包含最新的科技产品、数码设备、互联网动态等前沿科技资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"limit\":{\"type\":\"integer\",\"default\":20},\"offset\":{\"type\":\"integer\",\"default\":0}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>f0Uk75Pbfsx0rfdD725CYI</name>\n  <description>获取 InfoQ 技术资讯,包含软件开发、架构设计、云计算、AI等企业级技术内容和前沿开发者动态</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"region\":{\"type\":\"string\",\"enum\":[\"cn\",\"global\"],\"default\":\"cn\"}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fu70DSpIpWTVlq11tEKJZd</name>\n  <description>获取掘金文章榜,包含前端开发、后端技术、人工智能、移动开发及技术架构等领域的高质量中文技术文章和教程</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"category_id\":{\"anyOf\":[{\"type\":\"string\",\"const\":\"6809637769959178254\",\"description\":\"后端\"},{\"type\":\"string\",\"const\":\"6809637767543259144\",\"description\":\"前端\"},{\"type\":\"string\",\"const\":\"6809635626879549454\",\"description\":\"Android\"},{\"type\":\"string\",\"const\":\"6809635626661445640\",\"description\":\"iOS\"},{\"type\":\"string\",\"const\":\"6809637773935378440\",\"description\":\"人工智能\"},{\"type\":\"string\",\"const\":\"6809637771511070734\",\"description\":\"开发工具\"},{\"type\":\"string\",\"const\":\"6809637776263217160\",\"description\":\"代码人生\"},{\"type\":\"string\",\"const\":\"6809637772874219534\",\"description\":\"阅读\"}],\"default\":\"6809637769959178254\"}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fZMjSXkog94GRA7VoZpJtw</name>\n  <description>获取网易新闻热点榜,包含时政要闻、社会事件、财经资讯、科技动态及娱乐体育的全方位中文新闻资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>f5s3U6zXATp3L6wpAwNcn4</name>\n  <description>获取纽约时报新闻,包含国际政治、经济金融、社会文化、科学技术及艺术评论的高质量英文或中文国际新闻资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"region\":{\"anyOf\":[{\"type\":\"string\",\"const\":\"cn\",\"description\":\"中文\"},{\"type\":\"string\",\"const\":\"global\",\"description\":\"全球\"}],\"default\":\"cn\"},\"section\":{\"type\":\"string\",\"default\":\"HomePage\",\"description\":\"分类,当 `region``cn` 时无效。可选值: Africa, Americas, ArtandDesign, Arts, AsiaPacific, Automobiles, Baseball, Books/Review, Business, Climate, CollegeBasketball, CollegeFootball, Dance, Dealbook, DiningandWine, Economy, Education, EnergyEnvironment, Europe, FashionandStyle, Golf, Health, Hockey, HomePage, Jobs, Lens, MediaandAdvertising, MiddleEast, MostEmailed, MostShared, MostViewed, Movies, Music, NYRegion, Obituaries, PersonalTech, Politics, ProBasketball, ProFootball, RealEstate, Science, SmallBusiness, Soccer, Space, Sports, SundayBookReview, Sunday-Review, Technology, Television, Tennis, Theater, TMagazine, Travel, Upshot, US, Weddings, Well, World, YourMoney\"}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fSodMRu-GB5-mpBxBvxc2D</name>\n  <description>获取什么值得买热门,包含商品推荐、优惠信息、购物攻略、产品评测及消费经验分享的实用中文消费类资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"unit\":{\"anyOf\":[{\"type\":\"number\",\"const\":1,\"description\":\"今日热门\"},{\"type\":\"number\",\"const\":7,\"description\":\"周热门\"},{\"type\":\"number\",\"const\":30,\"description\":\"月热门\"}],\"default\":1}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fnY78eScFYQ-6xtUUQg8fB</name>\n  <description>获取少数派热榜,包含数码产品评测、软件应用推荐、生活方式指南及效率工作技巧的优质中文科技生活类内容</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"tag\":{\"type\":\"string\",\"enum\":[\"热门文章\",\"应用推荐\",\"生活方式\",\"效率技巧\",\"少数派播客\"],\"default\":\"热门文章\",\"description\":\"分类\"},\"limit\":{\"type\":\"integer\",\"default\":40}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fFlnyuBJfPLifqYRkW94Lh</name>\n  <description>获取腾讯新闻热点榜,包含国内外时事、社会热点、财经资讯、娱乐动态及体育赛事的综合性中文新闻资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"page_size\":{\"type\":\"integer\",\"default\":20}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>f0YfISsRrFbNGGwO3XVCFY</name>\n  <description>获取澎湃新闻热榜,包含时政要闻、财经动态、社会事件、文化教育及深度报道的高质量中文新闻资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fIKw7RiYt2oAptPSBtelf-</name>\n  <description>获取 The Verge 新闻,包含科技创新、数码产品评测、互联网趋势及科技公司动态的英文科技资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fH1Xj1bmY_qWxS6b8BoSCK</name>\n  <description>获取今日头条热榜,包含时政要闻、社会事件、国际新闻、科技发展及娱乐八卦等多领域的热门中文资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fIoNHXnzDif1o8sJSRpVBu</name>\n  <description>获取微博热搜榜,包含时事热点、社会现象、娱乐新闻、明星动态及网络热议话题的实时热门中文资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fX_nTem-9mBD-9Th_ZVRdA</name>\n  <description>获取微信读书排行榜,包含热门小说、畅销书籍、新书推荐及各类文学作品的阅读数据和排名信息</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"category\":{\"anyOf\":[{\"type\":\"string\",\"const\":\"rising\",\"description\":\"飙升榜\"},{\"type\":\"string\",\"const\":\"hot_search\",\"description\":\"热搜榜\"},{\"type\":\"string\",\"const\":\"newbook\",\"description\":\"新书榜\"},{\"type\":\"string\",\"const\":\"general_novel_rising\",\"description\":\"小说榜\"},{\"type\":\"string\",\"const\":\"all\",\"description\":\"总榜\"}],\"default\":\"rising\",\"description\":\"排行榜分区\"}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n\n<tool>\n  <name>fzIq8ORLIZHJLRU6pJt3O5</name>\n  <description>获取知乎热榜,包含时事热点、社会话题、科技动态、娱乐八卦等多领域的热门问答和讨论的中文资讯</description>\n  <arguments>\n    {\"type\":\"object\",\"properties\":{\"limit\":{\"type\":\"number\",\"default\":50}},\"additionalProperties\":false,\"$schema\":\"http://json-schema.org/draft-07/schema#\"}\n  </arguments>\n</tool>\n\n</tools>\n\n## Tool Use Rules\nHere are the rules you should always follow to solve your task:\n1. Always use the right arguments for the tools. Never use variable names as the action arguments, use the value instead.\n2. Call a tool only when needed: do not call the search agent if you do not need information, try to solve the task yourself.\n3. If no tool call is needed, just answer the question directly.\n4. Never re-do a tool call that you previously did with the exact same parameters.\n5. For tool use, MARK SURE use XML tag format as shown in the examples above. Do not use any other format.\n\n# User Instructions\n\n\nNow Begin! If you solve the task correctly, you will receive a reward of $1,000,000.\n"
}

主要包括:

  • 工具使用格式 - 使用XML风格的标签来调用工具,包括工具名称和JSON格式的参数;
  • 工具使用示例 - 展示了如何使用各种假设工具的例子,如文档问答、图像生成、Python解释器等;
  • 可用工具列表 - 提供了多个实际可用的信息获取工具,主要是各种中英文新闻和内容平台的热门榜单;
  • 工具使用规则 - 强调了正确使用参数、仅在需要时调用工具、不重复调用等规则;
  • 最后,提示词以一个有趣的激励结束,表示如果任务正确完成,将获得一百万美元奖励。

index =1 的用户的内容


{
  "role": "user",
  "content": "帮我搜索 模型上下文协议 MCP 相关的最新技术文章"
}

index =2 的助手的内容


{
  "role": "assistant",
  "content": "为了找到关于模型上下文协议(MCP)的最新技术文章,我将使用一些可用的工具来搜索相关资讯。首先,我可以从InfoQ开始,因为它经常发布企业级技术内容和前沿开发者动态。\n\n<tool_use>\n  <name>f0Uk75Pbfsx0rfdD725CYI</name>\n  <arguments>{\"region\":\"global\"}</arguments>\n</tool_use>"
}

index =3 的 用户的内容


{
  "role": "user",
  "content": [
    {
      "type": "text",
      "text": "Here is the result of tool call f0Uk75Pbfsx0rfdD725CYI:"
    },
    {
      "type": "text",
      "text": "[{\"type\":\"text\",\"text\":\"<title>Docker Desktop 4.40 Introduces Model Runner to Run LLMs Locally Expanding its AI Capabilities</title>\\n<description> 省略其他}]"
    }
  ]
}

img

第三次调用主要是为了给话题起标题。

大家,可以多开启几个工具或者多问几次,结合理论部分的讲解,会对 MCP 的过程会有更深刻的体会。

四、如何学习大模型 AI ?

由于新岗位的生产效率,要优于被取代岗位的生产效率,所以实际上整个社会的生产效率是提升的。

但是具体到个人,只能说是:

“最先掌握AI的人,将会比较晚掌握AI的人有竞争优势”。

这句话,放在计算机、互联网、移动互联网的开局时期,都是一样的道理。

我在一线科技企业深耕十二载,见证过太多因技术卡位而跃迁的案例。那些率先拥抱 AI 的同事,早已在效率与薪资上形成代际优势,我意识到有很多经验和知识值得分享给大家,也可以通过我们的能力和经验解答大家在大模型的学习中的很多困惑。我们整理出这套 AI 大模型突围资料包

  • ✅ 从零到一的 AI 学习路径图
  • ✅ 大模型调优实战手册(附医疗/金融等大厂真实案例)
  • ✅ 百度/阿里专家闭门录播课
  • ✅ 大模型当下最新行业报告
  • ✅ 真实大厂面试真题
  • ✅ 2025 最新岗位需求图谱

所有资料 ⚡️ ,朋友们如果有需要 《AI大模型入门+进阶学习资源包》下方扫码获取~
在这里插入图片描述

① 全套AI大模型应用开发视频教程

(包含提示工程、RAG、LangChain、Agent、模型微调与部署、DeepSeek等技术点)
在这里插入图片描述

② 大模型系统化学习路线

作为学习AI大模型技术的新手,方向至关重要。 正确的学习路线可以为你节省时间,少走弯路;方向不对,努力白费。这里我给大家准备了一份最科学最系统的学习成长路线图和学习规划,带你从零基础入门到精通!
在这里插入图片描述

③ 大模型学习书籍&文档

学习AI大模型离不开书籍文档,我精选了一系列大模型技术的书籍和学习文档(电子版),它们由领域内的顶尖专家撰写,内容全面、深入、详尽,为你学习大模型提供坚实的理论基础。
在这里插入图片描述

④ AI大模型最新行业报告

2025最新行业报告,针对不同行业的现状、趋势、问题、机会等进行系统地调研和评估,以了解哪些行业更适合引入大模型的技术和应用,以及在哪些方面可以发挥大模型的优势。
在这里插入图片描述

⑤ 大模型项目实战&配套源码

学以致用,在项目实战中检验和巩固你所学到的知识,同时为你找工作就业和职业发展打下坚实的基础。
在这里插入图片描述

⑥ 大模型大厂面试真题

面试不仅是技术的较量,更需要充分的准备。在你已经掌握了大模型技术之后,就需要开始准备面试,我精心整理了一份大模型面试题库,涵盖当前面试中可能遇到的各种技术问题,让你在面试中游刃有余

图片

以上资料如何领取?

在这里插入图片描述

为什么大家都在学大模型?

最近科技巨头英特尔宣布裁员2万人,传统岗位不断缩减,但AI相关技术岗疯狂扩招,有3-5年经验,大厂薪资就能给到50K*20薪!

图片

不出1年,“有AI项目经验”将成为投递简历的门槛。

风口之下,与其像“温水煮青蛙”一样坐等被行业淘汰,不如先人一步,掌握AI大模型原理+应用技术+项目实操经验,“顺风”翻盘!
在这里插入图片描述
在这里插入图片描述

这些资料真的有用吗?

这份资料由我和鲁为民博士(北京清华大学学士和美国加州理工学院博士)共同整理,现任上海殷泊信息科技CEO,其创立的MoPaaS云平台获Forrester全球’强劲表现者’认证,服务航天科工、国家电网等1000+企业,以第一作者在IEEE Transactions发表论文50+篇,获NASA JPL火星探测系统强化学习专利等35项中美专利。本套AI大模型课程由清华大学-加州理工双料博士、吴文俊人工智能奖得主鲁为民教授领衔研发。

资料内容涵盖了从入门到进阶的各类视频教程和实战项目,无论你是小白还是有些技术基础的技术人员,这份资料都绝对能帮助你提升薪资待遇,转行大模型岗位。
在这里插入图片描述
在这里插入图片描述

以上全套大模型资料如何领取?

在这里插入图片描述

Logo

更多推荐