Neuro Vault MCP

🧠💾 Plug your knowledge in like a USB drive. Your Obsidian vault, available in every AI conversation — search it, query it, write to it. Same vault in Claude Code, Cursor, Windsurf — no copy-paste, no context-switching, no re-indexing.

https://github.com/user-attachments/assets/0ba43373-3f97-4dc6-ab91-4f30bdafd0bf

Your second brain stops being a folder you open between contexts and becomes a first-class participant in every project. Ask, recall, decide, write back — all without leaving the conversation.

"What did I write about that idea last month?" — and now your assistant can actually answer.

✨ Why Neuro Vault?

• 🧠 Semantic search that already knows your vault — reuses Smart Connections embeddings. No re-indexing, no API keys, no extra infrastructure.
• 🎯 Quick or deep, your call — fast direct lookups for "find that note", or exploratory mode with related-note expansion when the question is fuzzy.
• 🧭 A real navigation toolkit for your agent — instead of grepping files and opening notes one by one, your assistant walks the vault like a database: filter by tags and properties, batch-read metadata, traverse the wikilink graph, discover the structure, jump to semantic neighbours.
• 🔎 Ask structured questions in plain language — "active projects tagged #ai", "todo tasks with a deadline this week", "meeting notes from Work/ newest first" — one call, ranked answer, no chains of reads.
• ✍️ Full write surface for your notes — create, in-place replace, or rewrite the whole body; manage frontmatter, tags, and daily notes. Frontmatter and creation route through the Obsidian CLI so Smart Connections, sync, and other plugins stay in the loop; in-place edits write directly to disk and the watcher catches up.
• ⚡ Zero infrastructure — local stdio MCP server, in-memory index, no database, no background processes, no watchers.
• 🔌 Drop-in for any MCP client — Claude Code, Cursor, Windsurf — configuration is a single JSON block.

🧰 Two superpowers, one server

Most "vault MCP" servers give you one or the other. Neuro Vault gives you both, and lets your assistant pick the right one per question:

The two work together: semantic search finds the right region of the vault, vault operations let the assistant actually do something with what it found.

✨ What it looks like in practice

Before: "Could you check my notes about that LangGraph experiment?" → Assistant lists Notes/, opens 12 files, greps for "LangGraph", gives up halfway, you paste the relevant note manually.

After: "Could you check my notes about that LangGraph experiment?" → One semantic search, top-3 ranked notes back, follow-up question already grounded in your own writing.

A few more questions Neuro Vault makes one-shot:

"What are my active projects tagged #ai with a deadline this quarter?" "Show meeting notes from Work/ from the last two weeks, newest first." "Find notes similar to this one I'm reading." "Append today's decision to the daily note." "What did past-me write about retrieval policy before I started building it?"

One question, one answer. Your assistant stops being a file browser and starts being an actual second brain.

→ See docs/guide/vault-operations.md for the full query language and examples.

🔍 Hybrid search: scope semantic with structural filters

search_notes accepts an optional filter to narrow the candidate set before semantic ranking — combining the precision of query_notes with the recall of vector search. Useful when domain-relevant notes are crowded out by larger narrative clusters.

{ "query": "trading lessons", "filter": { "tags": ["trading"] } }

filter accepts path_prefix, tags (ANY-of), and a frontmatter sift filter. Composition is filter AND threshold AND semantic. See the Semantic Search guide for full details.

🏗 How it works

flowchart LR
    You([You]) --> AI[AI assistant]
    AI <-->|MCP| NV[Neuro Vault]
    NV <--> Vault[(Obsidian vault)]

You ask, the assistant calls Neuro Vault, Neuro Vault reads your vault — semantic search uses embeddings already in .smart-env/, vault operations go through the obsidian CLI. No database, no background processes.

For module wiring and internal data flow, see docs/architecture/module-structure.md.

⚡ Quickstart

npm install -g neuro-vault-mcp

Add to your MCP client config (here: Claude Code's ~/.claude/settings.json):

{
  "mcpServers": {
    "neuro-vault": {
      "command": "neuro-vault-mcp",
      "args": ["--vault", "/absolute/path/to/your/vault"]
    }
  }
}

Then ask your assistant:

"What did I write about building AI agents?"

On first run the embedding model downloads automatically (~40 MB). Subsequent starts are fast.

For other clients (Cursor / Windsurf / npx), see docs/guide/installation.md.

📚 Documentation

User guide lives in docs/guide/:

• Installation
• Semantic Search — search_notes, get_similar_notes, find_duplicates, get_stats
• Vault Operations — note CRUD, daily notes, properties, tags, structured queries (query_notes)
• Routing Between Tools
• Configuration — CLI args, troubleshooting, limitations, migration to 2.0, development

Architecture / internals: docs/architecture/.

📄 License

ISC — see LICENSE.

Changelog: Releases