Local semantic search over your Obsidian vault - always fresh, never reindex.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
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.

bge-m3), your notes never leave your machinebge-m3 handles Korean, Japanese, and 100+ languages that English-only defaults fail onPrerequisites: Node 20+ and Ollama.
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.
Claude Code one-liner:
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"
Register one server per vault β index files are kept per-vault automatically:
Anything speaking /v1/embeddings works; FRESHVAULT_EMBED_KEY for authenticated endpoints (never written to the config file).
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 |
| β | FRESHVAULT_EMBED_API | ollama (or openai) |
| β | FRESHVAULT_EMBED_URL | http://localhost:1234 (openai mode) |
| β | FRESHVAULT_EMBED_KEY | none (openai mode, optional) |
| β | FRESHVAULT_IGNORE | none β e.g. Templates/,Daily/** (or ignore: [] in config) |
| β | FRESHVAULT_LEXICAL_GATE | on β lexical scoring for code-like query tokens; off for pure dense (or lexicalGate: false in config) |
Commands: setup Β· serve (default) Β· index (manual escape hatch) Β· status
Patterns follow gitignore semantics, matched against vault-relative paths:
| Pattern | Excludes |
|---|---|
Templates/ | any Templates directory at any depth β Templates/, work/Templates/ |
/Templates | only the vault-root Templates/ |
Daily/** | everything under the root-level Daily/ only β 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 |
* 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.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-rootTemplates/and silently indexed every nested one β 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.
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 β dense, hybrid-always, and the shipped gated mode β 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.
MIT Β© Kioko Lab
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/freshvault)<a href="https://allmcps.com/mcp/freshvault"><img src="https://allmcps.com/api/badge/freshvault?style=directory" alt="Freshvault on AllMCPs" /></a>