Synapse
About
MCP server that connects any AI to your Obsidian vault — save articles, search notes, build a compounding knowledge base
Details
- Author
- tomjrworks
- Categories
- Productivity, Other, Knowledge Base
Jump to
Setup
Install Synapse in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/tomjrworks/synapse-obsidian
Follow the installation instructions in the repository README, then restart your MCP client.
MCP server that connects any AI client — Claude, ChatGPT, Cursor, Windsurf — to your Obsidian vault. Save anything from anywhere, ask questions across your notes, keep the knowledge base your AI reads from.
- Open config:Mac~/Library/Application Support/Claude/claude_desktop_config.json|Windows%APPDATA%\Claude\claude_desktop_config.json
- Add Taproot to themcpServersobject:
{ "mcpServers": { "taproot": { "command": "npx", "args": ["-y", "synapse-obsidian", "/path/to/your/obsidian-vault"] } } }
- Restart Claude Desktop. Taproot tools appear automatically.
Add to.claude/.mcp.jsonin your home directory:
{ "mcpServers": { "taproot": { "command": "npx", "args": ["-y", "synapse-obsidian", "/path/to/your/vault"] } } }
Run Taproot locally and expose it with a free tunnel:
# Terminal 1: Start Taproot npx synapse-obsidian /path/to/vault --http --port 3777 # Terminal 2: Expose it (free, no account needed) npx cloudflared tunnel --url http://localhost:3777
Copy the tunnel URL. Addhttps://your-tunnel-url.trycloudflare.com/mcpas a custom MCP integration in your AI client.
"Help me get started with Taproot"
Taproot scans your vault and gives you three options:
- Use my existing vault— Detects your folder structure, wikilinks, naming conventions. Nothing moved or overwritten. Taproot adapts to you.
- Set up a knowledge base— Creates organized folders:sources/for raw content,notes/for compiled knowledge,outputs/for query results. Best for a focused research topic.
- Custom— You tell Taproot how you want things organized.
It also asks what you'll use the vault for (research, business, academic, life OS) so it can tailor the experience.
"Save this article:https://example.com/interesting-post"
Fetches the page, converts to markdown, saves to your vault. Works from your phone.
"What do my notes say about pricing strategy?"
Searches your vault, reads relevant files, synthesizes a cited answer.
"Process all new articles in my vault"
Turns raw sources into summaries, concept pages, entity pages — all cross-linked with wikilinks. Every answer feeds back into the knowledge base.
"Run a health check on my vault"
Finds broken links, orphan pages, missing frontmatter, stale content. Fixes what it can.
- Stdio(default) — For desktop AI apps (Claude Desktop, etc.)
- HTTP(--http) — For browser-based AI (Claude.ai, ChatGPT, etc.) behind Tailscale or another tunnel
Your vault is just a folder of markdown files. Taproot doesn't need Obsidian to be running — it works with any folder.
MCP server for Apple Notes with semantic search and CRUD operations. Claude searches, reads, creates, updates, and manages your Apple Notes through natural language.
Integrates Model Context Protocol (MCP) with Obsidian, allowing AI assistants to interact with your notes and vault.
A Model Context Protocol (MCP) Server for https://joplinapp.org/ that enables note access through the https://modelcontextprotocol.io. Perfect for integration with AI assistants like Claude.
A service for reading, writing, and managing markdown documentation with frontmatter metadata.
Connect your AI assistant to your personal knowledge base. Search, save links, create notes and to-dos. AI processes everything automatically.
An MCP server for interacting with Obsidian notes. Requires the OBSIDIAN_VAULT_PATH environment variable to be set.
Interact with your Obsidian vault using natural language.
Interact with your Obsidian vault using the Local REST API plugin, enabling LLMs to access and manage your notes.
Interact with your Obsidian notes and vaults using the Local REST API plugin.
A server for interacting with your Obsidian vault.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
