Your Obsidian vault is Claude's memory — local semantic search via MCP, always fresh, never reindex
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add freshvault -- npx -y freshvault{
"mcpServers": {
"freshvault": {
"command": "npx",
"args": ["-y", "freshvault"],
"env": {
"FRESHVAULT_EMBED_URL": "<freshvault_embed_url>"
}
}
}
}FRESHVAULT_EMBED_URLMCP Servers overview
# freshvault
[](https://github.com/KIOKO-LAB/freshvault/actions/workflows/ci.yml)
[](https://www.npmjs.com/package/freshvault)
[](https://registry.modelcontextprotocol.io/v0/servers?search=freshvault)

[한국어](./README.ko.md) · [日本語](./README.ja.md)
**Your Obsidian vault is Claude's memory. Always fresh, always local.**
Every other vault-search MCP makes you re-run an index command, babysit a watch terminal, or click "Update Index" in a web UI. freshvault watches your vault from *inside* the MCP server: edit a note, and Claude sees it seconds later. Automatically. Forever.

- 🔄 **Never reindex** — the file watcher lives in the server process; boot catch-up absorbs offline edits
- 🔒 **100% local** — embeddings via Ollama (`bge-m3`), your notes never leave your machine
- 🌏 **Multilingual by default** — `bge-m3` handles Korean, Japanese, and 100+ languages that English-only defaults fail on
- 🎯 **Benchmark-driven retrieval** — unconditional BM25 fusion wrecked Korean paraphrase queries (82.5% → 47.5% top-1), so it's off; pure dense missed identifier queries outright (57.1%), so it's not gone either. Lexical scoring is **gated on code-like query tokens**: paraphrase 82.5% → 82.5% (identical), identifiers 57.1% → 100% — [receipts](docs/ko-bench.md)
- 🪶 **No vector DB, no Docker, no Python** — JSON metadata + a Float32 sidecar, plain Node, source you can read in one sitting
- 🧠 **Chunking that respects sentences** — YAML frontmatter stripped, splits on paragraph/sentence boundaries (CJK-aware)
## Install
Prerequisites: [Node 20+](https://nodejs.org) and [Ollama](https://ollama.com).
```bash
npx -y freshvault setup
```
That's it. The wizard detects your Obsidian vault, pulls the embedding model, builds the index, and registers with Claude Code. There is no step 2, and there is never a step 2: no `index` command to re-run, no `watch` terminal, no background service.
<details>
<summary>Manual install (Claude Desktop / Cursor / Windsurf)</summary>
```json
{
"mcpServers": {
"freshvault": {
"command": "npx",
"args": ["-y", "freshvault", "serve"],
"env": { "FRESHVAULT_VAULT": "/absolute/path/to/your/vault" }
}
}
}
```
Claude Code one-liner:
```bash
claude mcp add freshvault -s user -- npx -y freshvault serve
```
</details>
## Use
Just ask Claude about your notes:
> "Search my notes for what I wrote about cache eviction strategies"
Three tools, all read-only:
| tool | what it does |
|---|---|
| `search_notes` | semantic search + optional `folder` / `tags` / `modified_after` / `modified_before` scoping; exact-title lookups boosted; at most 2 chunks per note so one long note can't own the results (`max_per_file`) |
| `get_note_context` | full note + its backlinks/outlinks from the vault link graph (path-traversal safe) |
| `index_status` | freshness report: notes/chunks, excluded count, last sync, watcher state |
Scoped queries competitors gate behind settings or paywalls work per-query here:
> "Search my notes tagged #project modified after June for the budget discussion"
## How it works
```
Obsidian vault ──fs.watch──▶ freshvault MCP server ──search_notes──▶ Claude
(.md files) (chunks → bge-m3 embeddings (generation)
→ one JSON index, incremental)
```
- **Incremental**: only changed/deleted notes are re-embedded (mtime+size diff), debounced 4s
- **Safety net**: a 60s mtime sweep catches events the watcher misses (network drives, atomic-rename editors)
- **Multi-client safe**: first server process becomes the writer (heartbeated lock); others are readers that hot-reload and promote themselves if the writer dies
- **Transactional**: an embedding-server outage mid-index can never lose or corrupt notes
- **Scale**: vectors live in a packed Float32 sidecar (fast startup, compact); brute-force cosine over thousands of chunks is milliseconds. Honest note: search is still linear — sub-100ms into tens of thousands of chunks, but this is not a vector DB replacement for huge corpora
### Multiple vaults
Register one server per vault — index files are kept per-vault automatically:
```bash
claude mcp add work-vault -s user -e FRESHVAULT_VAULT=/path/to/work -- npx -y freshvault serve
claude mcp add personal-vault -s user -e FRESHVAULT_VAULT=/path/to/personal -- npx -y freshvault serve
```
### Other embedding servers (LM Studio, LiteLLM, OpenAI-compatible)
```bash
FRESHVAULT_EMBED_API=openai FRESHVAULT_EMBED_URL=http://localhost:1234 npx -y freshvault serve
```
Anything speaking `/v1/embeddings` works; `FRESHVAULT_EMBED_KEY` for authenticated endpoints (never written to the config file).
## Configuration
Everything works with zero config after `setup`. Override when needed:
| Flag | Env | Default |
|---|---|---|
| `--vault` | `FRESHVAULT_VAULT` | from `setup` |
| `--model` | `FRESHVAULT_MODEL` | `bge-m3` |
| `--ollama-url` | `FRESHVAULT_OLLAMA_URL` | `http://localhost:11434` |
| `--data` | `FRESHVAULT_DATA` | platform data dir |
| — | `FRESHVAULT_EMBED_API` | `ollama` (or `openai`) |
| — | `FRESHVAULT_EMBED_URL` | `http://localhost:1234` (openai mode) |
| — | `FRESHVAULT_EMBED_KEY` | none (openai mode, optional) |
| — | `FRESHVAULT_IGNORE` | none — e.g. `Templates/,Daily/**` (or `ignore: []` in config) |
| — | `FRESHVAULT_LEXICAL_GATE` | `on` — lexical scoring for code-like query tokens; `off` for pure dense (or `lexicalGate: false` in config) |
Commands: `setup` · `serve` (default) · `index` (manual escape hatch) · `status`
### Ignore patterns
Patterns follow **gitignore** semantics, matched against vault-relative paths:
| Pattern | Excludes |
|---|---|
| `Templates/` | any `Templates` directory at any depth — `Templates/`, `work/Templates/` |
| `/Templates` | only the vault-root `Templates/` |
| `Daily/**` | everything under the **root-level** `Daily/` only — the internal slash anchors it |
| `**/Daily/**` | everything under any `Daily/`, at any depth |
| `*.excalidraw.md` | that filename at any depth |
| `work/wip.md` | exactly that path, relative to the vault root |
- A slash **anywhere but the end** anchors the pattern to the vault root. A trailing slash only means "directory" — it does **not** anchor.
- `*` and `?` never cross a `/`. `**` crosses directories only as a whole path segment (`**/x`, `x/**`, `x/**/y`); glued inside a segment it collapses to a single `*`, as in git.
- Matches end on a segment boundary — `Templates` never matches `TemplatesOld`.
- `!` negation and character classes are **not** supported; such patterns match nothing.
- `FRESHVAULT_IGNORE` is comma-separated, so a pattern cannot contain a comma.
> **Behaviour change since v0.3.0.** v0.3.0 treated a *trailing* slash as a root anchor, so `Templates/` excluded only the vault-root `Templates/` and silently indexed every nested one — no warning, just a quietly polluted index. Patterns shaped like `Templates/`, `/Templates`, `**/x` and `a/**/b` now exclude **more** than before (`/Templates` previously matched nothing at all). Conversely, `**` glued inside a segment (`Daily**md`) no longer crosses `/`. Run `freshvault status` after upgrading and compare the excluded count if it matters to you.
## Benchmark
Two retrieval micro-benchmarks ship in-repo (`node scripts/bench.mjs`): **ko-bench** (30 Korean notes, 40 paraphrase queries) and **id-bench** (38 technical notes, 14 identifier queries). Both run under three scoring modes — dense, hybrid-always, and the shipped gated mode — and the script checks the no-regression contract itself. Results and the bge-m3-ko (85.0% top-1, 634MB) import guide in [docs/ko-bench.md](docs/ko-bench.md).
## Roadmap
- MCPB bundle for one-click Claude Desktop install
- Reranking pass for large vaults
- PDF text extraction at index time
## License
MIT © Kioko Lab
What people ask about freshvault
What is KIOKO-LAB/freshvault?
+
KIOKO-LAB/freshvault is mcp servers for the Claude AI ecosystem. Your Obsidian vault is Claude's memory — local semantic search via MCP, always fresh, never reindex It has 0 GitHub stars and its last recorded update is dated 2026-08-06.
How do I install freshvault?
+
You can install freshvault by cloning the repository (https://github.com/KIOKO-LAB/freshvault) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is KIOKO-LAB/freshvault safe to use?
+
Our security agent has analyzed KIOKO-LAB/freshvault and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains KIOKO-LAB/freshvault?
+
KIOKO-LAB/freshvault is maintained by KIOKO-LAB. The last recorded GitHub activity is dated 2026-08-06, with 0 open issues.
Are there alternatives to freshvault?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy freshvault to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/kioko-lab-freshvault)<a href="https://claudewave.com/repo/kioko-lab-freshvault"><img src="https://claudewave.com/api/badge/kioko-lab-freshvault" alt="Featured on ClaudeWave: KIOKO-LAB/freshvault" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!