KnowledgeHub Mobile Capture

KnowledgeHub Mobile Capture

Enables a secure append-only write service for mobile ChatGPT captures, storing text, voice transcriptions, and attachments as new files in a private GitHub KnowledgeHub repository without overwriting or deleting existing content.

Category
Visit Server

README

KnowledgeHub Mobile Capture

“云飞随手记”的手机端写入服务与 OpenAI 插件包。它把手机 ChatGPT 中的文字、语音转写和附件,以只新增、不覆盖的方式写入用户自己的 GitHub 私有 KnowledgeHub 仓库。

当前状态:代码与本地测试基线已具备;只有完成公网部署、OAuth 配置和手机实机验收后,个人 KnowledgeHub 才能把“手机随手记”标记为已启用。

系统边界

flowchart LR
    A["手机 ChatGPT\n云飞随手记"] -->|"OAuth + MCP"| B["Mobile Capture 服务"]
    B -->|"仅创建新文件"| C["GitHub 私有 KnowledgeHub"]
    C -->|"git pull"| D["本地 KnowledgeHub"]
    D --> E["Obsidian"]
    D --> F["Codex"]

服务只注册一个写工具:create_quick_capture。路径由服务端生成,客户端不能指定:

00-Inbox/Human/Quick-Captures/YYYY/MM/<时间戳>-<随机标识>.md
10-Sources/Attachments/Quick-Captures/YYYY/MM/<capture-key>/<文件名>

记录内容不会被当作命令执行,也不会自动整理、归档或创建任务。成功必须返回 stored: true、知识库路径和 Git commit SHA。

仓库组成

  • src/:MCP HTTP 服务、OAuth/API Key 校验、GitHub create-only 写入。
  • plugins/knowledgehub-mobile-capture/:可安装插件清单与手机捕获 Skill。
  • test/:路径边界、附件限制、create-only、失败语义测试。
  • docs/DEPLOYMENT.md:正式手机端部署和连接步骤。
  • docs/ACCEPTANCE.md:启用前必须完成的验收。

本地开发验证

本地 API Key 模式只用于开发和 Codex 调试,不能作为 ChatGPT 手机端正式认证方案

Copy-Item .env.example .env
# 编辑 .env 后,把变量导入当前终端
npm install
npm test
npm start

健康检查:GET http://localhost:8787/health。MCP 入口:POST http://localhost:8787/mcp,请求头为 Authorization: Bearer <CAPTURE_API_KEY>

正式手机端

正式模式必须设置 AUTH_MODE=oauth-jwt,使用支持 MCP OAuth 2.1 的身份提供方,并部署到公网 HTTPS。ChatGPT 不支持用用户自定义 API Key 代替这一认证流程。完整步骤见 部署说明

OpenAI 官方资料:

安全原则

  • GitHub Token 只存放在部署平台的 Secret 中,不进入仓库、插件或聊天。
  • Token 仅授权目标私有 KnowledgeHub 仓库的 Contents 读写。
  • 服务不提供修改、移动、覆盖或删除工具。
  • OAuth 模式强制校验发行方、受众、权限范围和用户 sub 白名单。
  • 附件默认最多 5 个、单个 10 MiB、合计 20 MiB;文字默认最多 1 MiB。
  • 附件已创建而最终笔记失败时不自动删除,回执会列出待人工检查路径。

与 KnowledgeHub 的关系

  • KnowledgeHub-Framework 定义契约。
  • KnowledgeHub-Setup 负责可选安装和引导。
  • 本仓库实现手机远程入口,不保存用户资料或凭据。
  • 用户自己的私有 KnowledgeHub 是唯一资料权威。

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured