Obsidian Scoped-write MCP

Obsidian Scoped-write MCP

Enables reading an entire Obsidian Vault while limiting Markdown creation and updates to two designated ChatGPT directories, with overwrite protection and backup safeguards.

Category
Visit Server

README

Obsidian Scoped-write MCP

访问指定 Obsidian Vault 的 MCP 服务。整个 Vault 可读取；创建和更新 Markdown 只允许两个 ChatGPT 专属目录：

  • 00-ChatGPT系统入口
  • 01-ChatGPT策略主脑

不提供删除、移动、重命名或非 Markdown 写入工具。

工具

  • list_directory：列出目录。
  • read_markdown：读取 Markdown。
  • search_markdown：搜索 Markdown；单次最多扫描 1000 个 Markdown、读取 64 MiB，并最多返回 100 条匹配。
  • get_file_info：查看大小、修改时间、SHA-256 和可写状态。
  • create_directory：在允许目录内创建一级普通子文件夹；父目录必须已存在。
  • create_markdown：在允许目录创建新文件，禁止覆盖。
  • update_markdown：使用预期 SHA-256 更新已有文件，更新前在 Vault 外备份；同一服务进程内对同一文件串行更新。

本地验证

npm ci
npm test

测试默认创建临时 Vault 和临时备份目录，不接触个人 Obsidian 数据。传入真实 Vault 路径时只运行读取测试，不执行写入。

安全边界

  • 写入目录由服务器端固定白名单控制，工具参数不能扩大范围。
  • 创建文件夹只允许一级操作；同名、隐藏目录、缺失父目录、越界和符号链接逃逸均拒绝。
  • 创建目标已存在时拒绝。
  • 更新前先调用 get_file_info，把返回的 sha256 作为 expected_sha256；检测到版本变化时会拒绝。同一 MCP 进程内的并发更新已串行化；Obsidian、同步软件等外部进程仍存在极小竞争窗口，因此这属于乐观并发保护，并非跨进程原子 CAS。
  • 更新前备份到当前 Windows 用户的本地应用数据目录；备份不在 Vault 和 Git 仓库中。
  • 绝对路径、越界路径、符号链接逃逸和非 Markdown 均被拒绝。

开发流程

  • main 始终保持可发布。
  • 所有仓库变更使用短生命周期分支和 Pull Request。
  • CI 通过后才能合并，默认使用 squash merge。
  • 架构、安全边界、数据格式、长期依赖或多个独立 PR 的大功能：父 Issue、Sub-issues、ADR、PR、CI 和回滚记录。
  • 小补丁：单一 Issue 或 PR、最小改动、最小测试和回滚说明。

轻量补丁验收

  • 验收：运行 npm test，并由 Pull Request 的 CI 检查通过后合并。
  • 回滚：在 GitHub 上还原对应的 squash commit。

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