MCP Docs - Overview
Introduction
- MCP (Model Context Protocol) is an open-source standard for connecting AI applications to external systems.
- Using MCP, AI applications like Claude or ChatGPT can connect to
- data sources (e.g. local files, databases)
- tools (e.g. search engines, calculators)
- workflows (e.g. specialized prompts)—enabling them to access key information and perform tasks.
- Think of MCP like a USB-C port for AI applications.
- Just as USB-C provides a standardized way to connect electronic devices
- MCP provides a standardized way to connect AI applications to external systems.
Why does MCP matter?
Depending on where you sit in the ecosystem, MCP can have a range of benefits.
- Developers
- MCP reduces development time and complexity when building, or integrating with, an AI application or agent.
- AI applications or agents
- MCP provides access to an ecosystem of data sources, tools and apps which will enhance capabilities and improve the end-user experience.
- End-users
- MCP results in more capable AI applications or agents which can access your data and take actions on your behalf when necessary.
All articles on this blog are licensed under CC BY-NC-SA 4.0 unless otherwise stated.
Related Articles
2026-03-02
MCP - Introduction
Background Generative AI applications are a great step forward as they often let the user interact with the app using natural language prompts. However, as more time and resources are invested in such apps, you want to make sure you can easily integrate functionalities and resources in such a way that it’s easy to extend, that your app can cater to more than one model being used, and handle various model intricacies. In short, building Gen AI apps is easy to begin with, but as they grow and become more c...
2026-03-03
MCP Docs - Architecture
Overview This overview of the Model Context Protocol (MCP) discusses its scope and core concepts, and provides an example demonstrating each core concept. Because MCP SDKs abstract away many concerns, most developers will likely find the data layer protocol section to be the most useful. It discusses how MCP servers can provide context to an AI application. Scope MCP focuses on context exchange MCP Specification A specification of MCP that outlines the implementation requirements for clients and s...
2026-03-10
MCP Docs - Authorization
Overview Learn how to implement secure authorization for MCP servers using OAuth 2.1 to protect sensitive resources and operations. Authorization in the Model Context Protocol (MCP) secures access to sensitive resources and operations exposed by MCP servers. If your MCP server handles user data or administrative actions, authorization ensures only permitted users can access its endpoints. MCP uses standardized authorization flows to build trust between MCP clients and MCP servers. Its design doesn’t focu...
2024-07-10
LLM Core - Model Structure
模型文件 模型文件，也叫模型权重，里面大部分空间存放的是模型参数 - 即权重（Weights）和偏置（Biases） 还有其它信息，如优化器状态和元数据等 文件格式 使用 PyTorch，后缀为 .pth 使用 TensorFlow 或者 Hugging Face Transformers，后缀为 .bin 在模型预训练后，可以保存模型，在生产环境，不建议保存模型架构 与 Python 版本和模型定义的代码紧密相关，可能存在兼容性问题 模型权重 - 推荐 1torch.save(model.state_dict(), 'model_weights.pth') 模型权重 + 模型架构 - 可能存在兼容性问题 1torch.save(model, model_path) 权重 + 偏置 权重 - 最重要的参数之一 在前向传播过程中，输入会与权重相乘，这是神经网络学习特征和模式的基本方式 权重决定了输入如何影响输出 偏置 - 调整输出 允许模型输出在没有输入或者所有输入都为 0 的时候，调整到某个基线值 $y=kx+b$ $k$ 为权重，$b$ ...
2026-04-07
Agentic Harness - Qoder
背景 不是让 Agent 更聪明，而是让错误不可发生 现象 Agent 写代码违反隐式架构规则，lint 失败后陷入修复循环，上下文窗口被塞满，最终偏离目标 根因 - Agent “看不见” “教得更好“（更长 prompt、更多示例、规范文档）有天花板 规则随代码演进、文档在 AI 不可达的地方、不同模型”常识”不一致 解法转向 Harness 工程的核心思路：从”教 Agent 怎么做“转向”让 Agent 自己验证做得对不对“ 靠 linter、测试、架构约束等机械化检查保证正确性，而非依赖 LLM 的”直觉” 本质是把 CI/CD 的拦截时机从合并前提前到写代码时 仓库是 Agent 的操作系统 把散落的知识收进仓库 精简为可按需加载的索引 只编码架构边界而非实现细节 人的角色从执行者变为系统设计者 类比 Harness = LLM 的操作系统，不是增强它的算力，而是给它一个可以可靠运行的环境 CPU LLM 计算能力极强 推理能力极强 不知道硬盘在哪、网络协议是什么 不知道分层规则、文件该放哪 需要 OS 来管理资源、提供抽...
2024-08-06
RAG - Methodology
场景识别 分析业务流程，找出业务中依赖大量知识和信息处理的环节 复杂决策环节 在需要多维度信息综合分析与判断的业务流程中，RAG 可以为决策者提供实时的信息支持 使用 LLM 从各种来源的信息提炼出关键点，加权求和 - 压缩和整理非格式化信息 重复性内容生成 企业中有大量重复且标准化的内容生成任务 可以用程序去归纳流程，用 LLM 和 RAG 去填充每个环节 用户交互场景 增加自然语言交互 识别问题，找出流程痛点，并识别 LLM 和 RAG 能发挥的作用 信息碎片化 + 难以系统化输出 使用 LLM 和 RAG 能够通过自动化整合固定信息源，定期获取信息 统一整理（或生成）到统一的知识库，将分散的知识转化为结构化输出 人工处理效率低下 通过 LLM 自动化任务，可以更专注于更有创造力的工作 小步快跑 + 快速迭代 - LLM 技术变化极快 MVP Minimum viable product 数据驱动的迭代优化 持续收集用户行为数据和反馈，通过 A/B 测试等方法，不断优化系统表现
