vault-mcp
A remote MCP server that enables language models to search, read, and write notes in an Obsidian vault organized with the PARA method, and save URLs as notes.
README
vault-mcp
A small remote MCP server that lets an LLM (claude.ai, Claude Code, mobile) search, read, and write an Obsidian vault organised with the PARA method — and save URLs as notes.
The server holds no LLM of its own. It is a deterministic set of tools; the
connecting model is the brain. When you ask it to "save this to my vault", the
model calls vault_taxonomy to see your folder structure, picks the right
folder itself, and calls vault_write.
Claude Desktop / claude.ai / Claude Code
│ HTTPS + GitHub OAuth (or Bearer token)
▼
reverse proxy / TLS ──► vault-mcp (this server) ──► ~/Obsidian/YourVault
Docs: Architecture · Authentication · Deployment · Changelog
Tools
| Tool | What it does |
|---|---|
vault_taxonomy |
Returns the folder tree, PARA policy, and subcategory whitelists so the model can choose a destination folder. |
vault_search |
semantic (hybrid vector search) or title (exact name/path lookup). |
vault_read |
Returns a note's content. Machine-generated index/log files and legacy dumps are blocked. |
vault_write |
Create / overwrite / append a note. The caller supplies the folder. Writes are restricted to PARA buckets; the vault root is never written. |
vault_save_url |
Fetch a URL, extract clean text, save it as a note, and return a small preview. |
Safety
- Every path is resolved and confined to the vault root — no
..traversal, no absolute paths, no symlink escapes. - Writes are allowed only under
01-Inbox/,10-Projects/,20-Areas/,30-Resources/,docs/. - Reads of regenerable index/map/log artifacts and legacy wiki backups are refused (they are huge and waste tokens).
- Auth is required: a static Bearer token or GitHub OAuth with a user allowlist (see Authentication).
Install
git clone https://github.com/KORThomasJeong/vault-mcp.git
cd vault-mcp
cp .env.example .env # then edit .env
uv sync
Generate an auth token:
python -c "import secrets; print(secrets.token_urlsafe(32))"
Configure
All config is via environment (see .env.example):
| Var | Required | Default | Notes |
|---|---|---|---|
VAULT_PATH |
✅ | — | Absolute path to the vault root. |
AUTH_MODE |
inferred | token | github | none. See Authentication. |
|
MCP_AUTH_TOKEN |
(none) | Bearer token (token mode). | |
GITHUB_CLIENT_ID / GITHUB_CLIENT_SECRET |
(none) | GitHub OAuth app credentials (github mode). | |
BASE_URL |
(none) | Public HTTPS URL of the server (github mode). | |
GITHUB_ALLOWED_USERS |
(none) | Comma-separated GitHub logins allowed to connect. Required in github mode. | |
MCP_HOST |
127.0.0.1 |
Use 0.0.0.0 when the proxy reaches it over the LAN (e.g. NPM in Docker), else 502. |
|
MCP_PORT |
8848 |
||
MCP_PATH |
/mcp |
||
FAST_SEARCH_BIN |
(none) | Warm semantic-search front-end, called <bin> "<query>" -n <limit>. Preferred over QMD_BIN. |
|
QMD_BIN |
qmd |
Fallback semantic search helper. Blank + no FAST_SEARCH_BIN → that mode is disabled. |
|
WIKI_QUERY_BIN |
wiki-query |
Title/path search helper. Blank → disabled. | |
SAVE_LINK_BIN |
obsidian-save-link |
URL→note helper. Blank → disabled. | |
INDEX_REBUILD_CMD |
(none) | Command run when a tool is called with rebuild_index=true. |
The search and URL-save tools shell out to optional companion CLIs. If you don't have them, those tools simply report that they're disabled — read/write/taxonomy still work.
Run
uv run vault-mcp
# serves Streamable HTTP at http://127.0.0.1:8848/mcp
Expose it through your existing reverse proxy (nginx / Nginx Proxy Manager /
Caddy / Cloudflare) so that https://your-host/mcp forwards to 127.0.0.1:8848.
Enable WebSocket/streaming pass-through and disable response buffering so SSE
works (for nginx: proxy_buffering off;, a long proxy_read_timeout).
Authentication
| Mode | How clients authenticate | Works with |
|---|---|---|
token |
Authorization: Bearer <token> header |
Claude Code (--header). Not the Claude Desktop / claude.ai custom-connector UI (no header field). |
github |
GitHub OAuth (browser), restricted to GITHUB_ALLOWED_USERS |
Claude Desktop / claude.ai remote connectors, Claude Code. |
none |
nothing | trusted/private networks only. |
github + token |
both at once (MultiAuth) | Desktop via OAuth and CLI/automation via token, one server. |
OAuth authenticates, the allowlist authorizes. In
githubmode the server refuses to start unlessGITHUB_ALLOWED_USERSis set — otherwise any GitHub account could connect, which is more open than a token.
Both at once: set
MCP_AUTH_TOKENalongsidegithubmode and the server accepts GitHub OAuth and the static token simultaneously (MultiAuth). Details in docs/AUTHENTICATION.md.
Set up GitHub OAuth (github mode)
- Register an OAuth App at https://github.com/settings/developers → New OAuth App:
- Homepage URL:
https://your-host - Authorization callback URL:
https://your-host/auth/callback
- Homepage URL:
- Copy the Client ID, generate a Client secret, and put them plus
BASE_URL=https://your-host,AUTH_MODE=github, andGITHUB_ALLOWED_USERS=<your-login>in.env. - Restart the server.
Connect from Claude Code
# token mode
claude mcp add --transport http vault https://your-host/mcp \
--header "Authorization: Bearer <your-token>"
# github mode (OAuth — opens a browser)
claude mcp add --transport http vault https://your-host/mcp
Connect from Claude Desktop / claude.ai
Settings → Connectors → add a custom connector pointing at https://your-host/mcp.
Use github mode — the desktop/web connector UI authenticates via OAuth and
has no field for a static Bearer token.
Develop
uv run --extra dev pytest
License
MIT
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.