Skip to content
Back to search

obsidian-mcp-tools

Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/jacksteamdev--obsidian-mcp-tools/badge.svg)](/listings/jacksteamdev--obsidian-mcp-tools)

HTML

<a href="/listings/jacksteamdev--obsidian-mcp-tools"><img src="/api/listings/jacksteamdev--obsidian-mcp-tools/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

> [!Important] > This plugin requires a secure server component that runs locally on your computer. The server is distributed as a signed executable, with its complete source code available in `packages/mcp-server/`. For details about our security measures and code signing process, see the [Security](#security) section.

1. Install the plugin from Obsidian's Community Plugins 2. Enable the plugin in Obsidian settings 3. Open the plugin settings 4. Click "Install Server" to download and configure the MCP server

Clicking the install button will:

- Download the appropriate MCP server binary for your platform - Configure Claude Desktop to use the server - Set up necessary permissions and paths

Installation Locations

- **Server Binary**: {vault}/.obsidian/plugins/obsidian-mcp-tools/bin/ - **Log Files**: - macOS: ~/Library/Logs/obsidian-mcp-tools - Windows: %APPDATA%\obsidian-mcp-tools\logs - Linux: ~/.local/share/obsidian-mcp-tools/logs

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 230 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # MCP Tools for Obsidian
  2. [![GitHub release (latest by date)](https://img.shields.io/github/v/release/jacksteamdev/obsidian-mcp-tools)](https://github.com/jacksteamdev/obsidian-mcp-tools/releases/latest)
  3. [![Build status](https://img.shields.io/github/actions/workflow/status/jacksteamdev/obsidian-mcp-tools/release.yml)](https://github.com/jacksteamdev/obsidian-mcp-tools/actions)
  4. [![License](https://img.shields.io/github/license/jacksteamdev/obsidian-mcp-tools)](LICENSE)
  5. [Features](#features) | [Installation](#installation) | [Configuration](#configuration) | [Troubleshooting](#troubleshooting) | [Security](#security) | [Development](#development) | [Support](#support)
  6. > **⚠️ Project Archived**
  7. >
  8. > I'm grateful to all the users who have downloaded this plugin over the past year. Watching the Obsidian store install count climb to 87k has been fun! I never expected it to become the #1 MCP-related Obsidian plugin.
  9. >
  10. > This project was originally a labor of love for my partner, who was using Obsidian and wanted to chat with her notes. We're not using Obsidian currently, so I have decided to step aside to allow plugin developers who have a vested interest in the Obsidian ecosystem to gain users.
  11. >
  12. > There are at least five alternatives published to the Obsidian Community Plugins store, with many more MCP-related beta plugins available through BRAT. I'm not going to make recommendations for a specific plugin; I'll leave that to the user's discretion.
  13. MCP Tools for Obsidian enables AI applications like Claude Desktop to securely access and work with your Obsidian vault through the Model Context Protocol (MCP). MCP is an open protocol that standardizes how AI applications can interact with external data sources and tools while maintaining security and user control. [^2]
  14. This plugin consists of two parts:
  15. 1. An Obsidian plugin that adds MCP capabilities to your vault
  16. 2. A local MCP server that handles communication with AI applications
  17. When you install this plugin, it will help you set up both components. The MCP server acts as a secure bridge between your vault and AI applications like Claude Desktop. This means AI assistants can read your notes, execute templates, and perform semantic searches - but only when you allow it and only through the server's secure API. The server never gives AI applications direct access to your vault files. [^3]
  18. > **Privacy Note**: When using Claude Desktop with this plugin, your conversations with Claude are not used to train Anthropic's models by default. [^1]
  19. ## Features
  20. When connected to an MCP client like Claude Desktop, this plugin enables:
  21. - **Vault Access**: Allows AI assistants to read and reference your notes while maintaining your vault's security [^4]
  22. - **Semantic Search**: AI assistants can search your vault based on meaning and context, not just keywords [^5]
  23. - **Template Integration**: Execute Obsidian templates through AI interactions, with dynamic parameters and content generation [^6]
  24. All features require an MCP-compatible client like Claude Desktop, as this plugin provides the server component that enables these integrations. The plugin does not modify Obsidian's functionality directly - instead, it creates a secure bridge that allows AI applications to work with your vault in powerful ways.
  25. ## Prerequisites
  26. ### Required
  27. - [Obsidian](https://obsidian.md/) v1.7.7 or higher
  28. - [Claude Desktop](https://claude.ai/download) installed and configured
  29. - [Local REST API](https://github.com/coddingtonbear/obsidian-local-rest-api) plugin installed and configured with an API key
  30. ### Recommended
  31. - [Templater](https://silentvoid13.github.io/Templater/) plugin for enhanced template functionality
  32. - [Smart Connections](https://smartconnections.app/) plugin for semantic search capabilities
  33. ## Installation
  34. > [!Important]
  35. > This plugin requires a secure server component that runs locally on your computer. The server is distributed as a signed executable, with its complete source code available in `packages/mcp-server/`. For details about our security measures and code signing process, see the [Security](#security) section.
  36. 1. Install the plugin from Obsidian's Community Plugins
  37. 2. Enable the plugin in Obsidian settings
  38. 3. Open the plugin settings
  39. 4. Click "Install Server" to download and configure the MCP server
  40. Clicking the install button will:
  41. - Download the appropriate MCP server binary for your platform
  42. - Configure Claude Desktop to use the server
  43. - Set up necessary permissions and paths
  44. ### Installation Locations
  45. - **Server Binary**: {vault}/.obsidian/plugins/obsidian-mcp-tools/bin/
  46. - **Log Files**:
  47. - macOS: ~/Library/Logs/obsidian-mcp-tools
  48. - Windows: %APPDATA%\obsidian-mcp-tools\logs
  49. - Linux: ~/.local/share/obsidian-mcp-tools/logs
  50. ## Configuration
  51. After clicking the "Install Server" button in the plugin settings, the plugin will automatically:
  52. 1. Download the appropriate MCP server binary
  53. 2. Use your Local REST API plugin's API key
  54. 3. Configure Claude Desktop to use the MCP server
  55. 4. Set up appropriate paths and permissions
  56. While the configuration process is automated, it requires your explicit permission to install the server binary and modify the Claude Desktop configuration. No additional manual configuration is required beyond this initial setup step.
  57. ## Troubleshooting
  58. If you encounter issues:
  59. 1. Check the plugin settings to verify:
  60. - All required plugins are installed
  61. - The server is properly installed
  62. - Claude Desktop is configured
  63. 2. Review the logs:
  64. - Open plugin settings
  65. - Click "Open Logs" under Resources
  66. - Look for any error messages or warnings
  67. 3. Common Issues:
  68. - **Server won't start**: Ensure Claude Desktop is running
  69. - **Connection errors**: Verify Local REST API plugin is configured
  70. - **Permission errors**: Try reinstalling the server
  71. ## Security
  72. ### Binary Distribution
  73. - All releases are built using GitHub Actions with reproducible builds
  74. - Binaries are signed and attested using SLSA provenance
  75. - Release workflows are fully auditable in the repository
  76. ### Runtime Security
  77. - The MCP server runs with minimal required permissions
  78. - All communication is encrypted
  79. - API keys are stored securely using platform-specific credential storage
  80. ### Binary Verification
  81. The MCP server binaries are published with [SLSA Provenance attestations](https://slsa.dev/provenance/v1), which provide cryptographic proof of where and how the binaries were built. This helps ensure the integrity and provenance of the binaries you download.
  82. To verify a binary using the GitHub CLI:
  83. 1. Install GitHub CLI:
  84. ```bash
  85. # macOS (Homebrew)
  86. brew install gh
  87. # Windows (Scoop)
  88. scoop install gh
  89. # Linux
  90. sudo apt install gh # Debian/Ubuntu
  91. ```
  92. 2. Verify the binary:
  93. ```bash
  94. gh attestation verify --owner jacksteamdev <binary path or URL>
  95. ```
  96. The verification will show:
  97. - The binary's SHA256 hash
  98. - Confirmation that it was built by this repository's GitHub Actions workflows
  99. - The specific workflow file and version tag that created it
  100. - Compliance with SLSA Level 3 build requirements
  101. This verification ensures the binary hasn't been tampered with and was built directly from this repository's source code.
  102. ### Reporting Security Issues
  103. Please report security vulnerabilities via our [security policy](SECURITY.md).
  104. Do not report security vulnerabilities in public issues.
  105. ## Development
  106. This project uses a monorepo structure with feature-based architecture. For detailed project architecture documentation, see [.clinerules](.clinerules).
  107. ### Using Cline
  108. Some code in this project was implemented using the AI coding agent [Cline](https://cline.bot). Cline uses `cline_docs/` and the `.clinerules` file to understand project architecture and patterns when implementing new features.
  109. ### Workspace
  110. This project uses a [Bun](https://bun.sh/) workspace structure:
  111. ```
  112. packages/
  113. ├── mcp-server/ # Server implementation
  114. ├── obsidian-plugin/ # Obsidian plugin
  115. └── shared/ # Shared utilities and types
  116. ```
  117. ### Building
  118. 1. Install dependencies:
  119. ```bash
  120. bun install
  121. ```
  122. 2. Build all packages:
  123. ```bash
  124. bun run build
  125. ```
  126. 3. For development:
  127. ```bash
  128. bun run dev
  129. ```
  130. ### Requirements
  131. - [bun](https://bun.sh/) v1.1.42 or higher
  132. - TypeScript 5.0+
  133. ## Contributing
  134. **Before contributing, please read our [Contributing Guidelines](CONTRIBUTING.md) including our community standards and behavioral expectations.**
  135. 1. Fork the repository
  136. 2. Create a feature branch
  137. 3. Make your changes
  138. 4. Run tests:
  139. ```bash
  140. bun test
  141. ```
  142. 5. Submit a pull request
  143. We welcome genuine contributions but maintain strict community standards. Be respectful and constructive in all interactions.
  144. ## Support
  145. - 💬 [Join our Discord](https://discord.gg/q59pTrN9AA) for questions, discussions, and community support
  146. - [Open an issue](https://github.com/jacksteamdev/obsidian-mcp-tools/issues) for bug reports and feature requests
  147. **Please read our [Contributing Guidelines](CONTRIBUTING.md) before posting.** We maintain high community standards and have zero tolerance for toxic behavior.
  148. ## Changelog
  149. See [GitHub Releases](https://github.com/jacksteamdev/obsidian-mcp-tools/releases) for detailed changelog information.
  150. ## License
  151. [MIT License](LICENSE)
  152. ## Footnotes
  153. [^1]: For information about Claude data privacy and security, see [Claude AI's data usage policy](https://support.anthropic.com/en/articles/8325621-i-would-like-to-input-sensitive-data-into-free-claude-ai-or-claude-pro-who-can-view-my-conversations)
  154. [^2]: For more information about the Model Context Protocol, see [MCP Introduction](https://modelcontextprotocol.io/introduction)
  155. [^3]: For a list of available MCP Clients, see [MCP Example Clients](https://modelcontextprotocol.io/clients)
  156. [^4]: Requires Obsidian plugin Local REST API
  157. [^5]: Requires Obsidian plugin Smart Connections
  158. [^6]: Requires Obsidian plugin Templater

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.