About
Obsidian GitHub MCP connects AI assistants to Obsidian vaults stored on GitHub repositories. It enables AI models to read, search, and analyze Markdown-based knowledge bases stored in version control. Key features of Obsidian GitHub MCP: - Retrieve specific notes and documents from Obsidian vaults via GitHub's API. - Multi-mode file search across filenames, file paths, and document contents. - Track knowledge base evolution with Git commit history and diffs. - Search GitHub issues to integrate project management with notes. - Compatible with Claude, Cursor, Windsurf, Cline, and other MCP hosts. - Full TypeScript implementation with Zod schema validation.
README
[](https://smithery.ai/server/@Hint-Services/obsidian-github-mcp) [](https://www.npmjs.com/package/obsidian-github-mcp)
Obsidian GitHub MCP
A Model Context Protocol (MCP) server that connects AI assistants to GitHub repositories containing Obsidian vaults. This server enables seamless integration with your knowledge base stored on GitHub, allowing AI assistants to read, search, and analyze your Obsidian notes and documentation.
Why This Tool?
Many Obsidian users store their vaults in GitHub for backup, versioning, and collaboration. This MCP server bridges the gap between your GitHub-hosted Obsidian vault and AI assistants, enabling:
Features
Available Tools
Knowledge Base Access
filename: Find files by exact filename (perfect for "OKR 2025" type searches)
- path: Search anywhere in file paths
- content: Search within file contents
- all: Comprehensive search across filenames, paths, and contentProject Management Integration
Use Cases
For Knowledge Workers
For Developers
For Students & Academics
Installation
Using Smithery (Recommended)
The easiest way to install Obsidian GitHub MCP is using Smithery:
# For Claude Desktop
npx -y @smithery/cli install @Hint-Services/obsidian-github-mcp --client claudeFor Cursor
npx -y @smithery/cli install @Hint-Services/obsidian-github-mcp --client cursorFor Windsurf
npx -y @smithery/cli install @Hint-Services/obsidian-github-mcp --client windsurfFor Cline
npx -y @smithery/cli install @Hint-Services/obsidian-github-mcp --client cline
Manual Installation
npm install obsidian-github-mcp
Configuration
Add the server to your MCP settings file with the following configuration:
{
"mcpServers": {
"obsidianGithub": {
"command": "npx",
"args": ["-y", "obsidian-github-mcp"],
"env": {
"GITHUB_TOKEN": "your-github-token",
"GITHUB_OWNER": "your-github-username",
"GITHUB_REPO": "your-obsidian-vault-repo"
}
}
}
}
Required Environment Variables
GITHUB_TOKEN: Your GitHub personal access token (create one here)GITHUB_OWNER: The owner/organization of the GitHub repositoryGITHUB_REPO: The name of the repository containing your Obsidian vaultGitHub Token Permissions
Your GitHub token needs the following permissions:
repo (for private repositories) or public_repo (for public repositories)read:org (if accessing organization repositories)Example Workflows
Accessing Your Daily Notes
{
"tool": "getFileContents",
"arguments": {
"filePath": "Daily Notes/2024-01-15.md"
}
}
Finding Files by Name (Perfect for "OKR 2025" example!)
{
"tool": "searchFiles",
"arguments": {
"query": "OKR 2025",
"searchIn": "filename"
}
}
Finding Files by Path
```json { "tool": "searchFiles", "arguments": { "query": "Daily Notes", "searchIn": "path"
Related MCP Servers
AI Research Assistant
hamid-vakilzadeh
AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar
Linkup
LinkupPlatform
Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages
Math-MCP
EthanHenrickson
Math-MCP is a computation server that enables Large Language Models (LLMs) to perform accurate numerical calculations through the Model Context Protocol. It provides precise mathematical operations via a simple API to overcome LLM limitations in arithmetic and statistical reasoning. Key features of Math-MCP: - Basic arithmetic operations: addition, subtraction, multiplication, division, modulo, and bulk summation - Statistical analysis functions: mean, median, mode, minimum, and maximum calculations - Rounding utilities: floor, ceiling, and nearest integer rounding - Trigonometric functions: sine, cosine, tangent, and their inverses with degrees and radians conversion support