freshvault
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-m3handles 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
- 🪶 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+ and Ollama.
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.
Manual install (Claude Desktop / Cursor / Windsurf)
{
"mcpServers": {
"freshvault": {
"command": "npx",
"args": ["-y", "freshvault", "serve"],
"env": { "FRESHVAULT_VAULT": "/absolute/path/to/your/vault" }
}
}
}
Claude Code one-liner:
claude mcp add freshvault -s user -- npx -y freshvault serve
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:
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)
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 —
Templatesnever matchesTemplatesOld. !negation and character classes are not supported; such patterns match nothing.FRESHVAULT_IGNOREis 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-rootTemplates/and silently indexed every nested one — no warning, just a quietly polluted index. Patterns shaped likeTemplates/,/Templates,**/xanda/**/bnow exclude more than before (/Templatespreviously matched nothing at all). Conversely,**glued inside a segment (Daily**md) no longer crosses/. Runfreshvault statusafter 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.
Roadmap
- MCPB bundle for one-click Claude Desktop install
- Reranking pass for large vaults
- PDF text extraction at index time
License
MIT © Kioko Lab