# Obsidian Semantic Search [Health: Active] **Category:** ๐Ÿ—„๏ธ Databases **Repository:** https://github.com/DalecB/obsidian-semantic-mcp **GitHub Stars:** 0 **Views:** 0 **Installs:** 0 **Upvotes:** 0 **Directory Page:** https://allmcps.com/mcp/obsidian-semantic-search ## Description Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings. ## Tools Capabilities this server exposes over MCP: - **index_status** โ€” Returns index metadata and safety settings. - **index_vault** โ€” Builds or updates the external SQLite index. - **search_notes** โ€” Searches notes with hybrid semantic and keyword ranking. - **read_note** โ€” Reads a note or line range by vault-relative path. ## Claude Desktop Quick Installation Install path detected from listing signals. Uses `npx` (confidence: high): ```json "mcpServers": { "obsidian-semantic-search": { "command": "npx", "args": ["-y","--package"] } } ``` ## Documentation & README

Obsidian Semantic Search MCP

Read-only semantic retrieval for agents that need to find the right Obsidian note without write access.

npm MCP Registry License Node.js

ํ•œ๊ตญ์–ด ยท Quick Start ยท Why This Exists ยท How It Works

--- Your Obsidian vault is useful only if your agent can find the right note. Keyword search misses context. Full write-capable Obsidian MCP servers expose more power than a retrieval agent needs. Obsidian plugins are great inside Obsidian, but they are not always the right boundary for Codex, Claude Desktop, Cursor, or any other MCP client. This project is the narrow version: ```text local Obsidian vault -> read-only scanner -> local SQLite index -> MCP search/read tools ``` No note writes. No cloud embeddings by default. No Obsidian plugin runtime. No sync service.

Local, read-only pipeline: Obsidian vault to scanner to chunker to Ollama embeddings to SQLite index, queried by an MCP client via search_notes and read_note

> Status: `0.3.1` early preview. The server is usable today, but ranking behavior and tool schemas may change before `1.0`. ## What You Get | Need | What this server does | | --- | --- | | Find the note an agent should read | Hybrid semantic + keyword search over Markdown notes | | Keep the vault safe | Exposes search/read/index/status only; no write, patch, move, rename, or delete tools | | Stay local-first | Uses Ollama embeddings and stores the index on your machine | | Make results agent-friendly | Returns file-level matches with headings, snippets, and line ranges | | Avoid plugin state | Reads the vault directly from the filesystem; Obsidian does not need to be running | Example result shape: ```json { "path": "02_Projects/RealtimeAPI/05_Interview_QA.md", "title": "Interview Q&A", "score": 0.7431, "matched_sections": [ { "heading": "Level 4 > Redis Lua atomicity", "lines": [266, 305], "reason": "semantic=1, keyword=0.5565, metadata=0.6" } ] } ``` ## Quick Start Requirements: - Node.js `>= 24` - Ollama - An Obsidian vault - An MCP client such as Codex, Claude Desktop, Cursor, or another stdio MCP client Install the embedding model: ```bash ollama pull bge-m3 curl http://localhost:11434/api/tags ``` Print setup guidance: ```bash npx -y --package @dalecb/obsidian-semantic-mcp obsidian-semantic-mcp-setup ``` ## Codex Setup Add this to `~/.codex/config.toml`: ```toml [mcp_servers.obsidian_semantic] command = "npx" args = ["-y", "@dalecb/obsidian-semantic-mcp"] [mcp_servers.obsidian_semantic.env] OBSIDIAN_VAULT_ROOT = "/path/to/your/Obsidian Vault" OBSIDIAN_SEMANTIC_MCP_HOME = "/Users/you/.obsidian-semantic-mcp" OLLAMA_BASE_URL = "http://localhost:11434" OBSIDIAN_EMBED_MODEL = "bge-m3" OBSIDIAN_SEMANTIC_AUTO_INDEX = "true" ``` Restart Codex, then run: ```text obsidian_semantic.index_status obsidian_semantic.search_notes { "query": "Redis Lua atomicity", "limit": 5 } ``` ## Claude Code Setup Add the server at user scope so the personal vault path stays out of project `.mcp.json` files: ```bash claude mcp add obsidian_semantic --scope user \ --env OBSIDIAN_VAULT_ROOT="/path/to/your/Obsidian Vault" \ --env OBSIDIAN_SEMANTIC_MCP_HOME="/Users/you/.obsidian-semantic-mcp" \ --env OLLAMA_BASE_URL="http://localhost:11434" \ --env OBSIDIAN_EMBED_MODEL="bge-m3" \ --env OBSIDIAN_SEMANTIC_AUTO_INDEX="true" \ -- npx -y @dalecb/obsidian-semantic-mcp claude mcp get obsidian_semantic ``` Start a new Claude Code session and run `/mcp` to confirm the server is connected. On native Windows, use `-- cmd /c npx -y @dalecb/obsidian-semantic-mcp` after the environment flags. See Anthropic's [Claude Code MCP documentation](https://docs.anthropic.com/en/docs/claude-code/mcp) for scope and command details. ## Claude Desktop / JSON MCP Client Setup In Claude Desktop, open **Settings โ†’ Developer โ†’ Edit Config**. This opens `~/Library/Application Support/Claude/claude_desktop_config.json` on macOS or `%APPDATA%\Claude\claude_desktop_config.json` on Windows. Merge the following server into `mcpServers`: ```json { "mcpServers": { "obsidian_semantic": { "command": "npx", "args": ["-y", "@dalecb/obsidian-semantic-mcp"], "env": { "OBSIDIAN_VAULT_ROOT": "/path/to/your/Obsidian Vault", "OBSIDIAN_SEMANTIC_MCP_HOME": "/Users/you/.obsidian-semantic-mcp", "OLLAMA_BASE_URL": "http://localhost:11434", "OBSIDIAN_EMBED_MODEL": "bge-m3", "OBSIDIAN_SEMANTIC_AUTO_INDEX": "true" } } } } ``` Fully quit and restart Claude Desktop. Cursor and other JSON-style stdio MCP clients can use the same `mcpServers` entry. On Windows, if `npx` is not found, use `"command": "cmd"` and prepend `"/c", "npx"` to `args`. See the official [local MCP server guide](https://modelcontextprotocol.io/docs/develop/connect-local-servers) for Claude Desktop configuration and logs. ## Why This Exists This isn't aiming to be the most powerful Obsidian automation server. It aims to be the safest retrieval tool you can hand an agent. Here's how it stacks up against the two tools it usually comes down to โ€” a full-permission Obsidian MCP server (Local REST API based) and GBrain (a broader knowledge-compilation platform): | | **This project** | **Full-permission Obsidian MCP** | **GBrain** | | --- | --- | --- | --- | | Access model | Read-only: search / read / index | Read + write + edit + delete | Read + write; compiles notes into its own model | | Touches your vault | Never | Yes | Yes โ€” restructures content | | Obsidian must run | No โ€” reads files directly | Yes โ€” needs the REST API plugin | No | | Required local runtime | Node.js + Ollama | Obsidian + plugin | Standalone platform | | Embeddings & data | Local Ollama by default; remote URL is configurable | Local API; embeddings vary by setup | Built-in pipeline; optional sync | | Storage | One SQLite file you can delete and rebuild | Plugin-managed | Its own store / migration | | Best for | A small read-only retrieval boundary for agents | Full vault automation and editing | Building a compiled knowledge base across sources | That trade is on purpose: give up writing, editing, and running inside Obsidian, and you get fewer moving parts and a smaller blast radius in return. Use this if your agent should answer: - "Which note explains this project decision?" - "Find the file where I wrote about idempotency payload mismatch." - "Show me the career notes related to this interview topic." - "Search my vault, but do not mutate it." Do not use this if you want an Obsidian UI plugin, automatic note generation, or write-capable vault automation. ## Tools ### `index_status` Returns index metadata and safety settings. ### `index_vault` Builds or updates the external SQLite index. ```json { "mode": "incremental" } ``` Specific files: ```json { "mode": "incremental", "paths": ["02_Projects/My Note.md"] } ``` ### `search_notes` Searches notes with hybrid semantic and keyword ranking. ```json { "query": "live coding notes", "limit": 8, "mode": "hybrid" } ``` Modes: - `hybrid`: semantic vector + SQLite FTS5 + metadata boosts - `semantic`: vector-first search - `keyword`: FTS5 keyword search without embedding the query ### `read_note` Reads a note or line range by vault-relative path. ```json { "path": "02_Projects/My Note.md", "start_line": 10, "end_line": 40 } ``` ## How It Works ```text index_vault -> scan Markdown files under OBSIDIAN_VAULT_ROOT -> block denied paths and symlink escapes -> split notes by Markdown headings -> create one summary chunk per file -> embed chunks with Ollama bge-m3 -> store notes, chunks, FTS rows, and vectors in SQLite search_notes -> incrementally index on first search or first search after a Markdown change -> embed the query with Ollama -> score vector similarity -> score SQLite FTS5 keyword matches -> apply title/path/heading metadata boosts -> regroup chunk matches into file-level results ``` Default storage: ```text ~/.obsidian-semantic-mcp/ data/semantic.sqlite ``` The vault remains the source of truth. The SQLite database is a derived index and can be deleted/rebuilt. ## Safety Model The server reads your vault and never writes to it. Three layers decide what an agent can see. **1. Always denied (system / tooling).** Never indexed, no override: - `.obsidian/`, `.smart-env/`, `.claude/`, `.codex-*/` - any hidden folder (name starts with `.`) - `node_modules`, `cache`, `logs` **2. Sensitive โ€” denied by default, unlockable.** Stays blocked even when a tool call passes `include_sensitive: true`, unless the server is started with `OBSIDIAN_SEMANTIC_ALLOW_SENSITIVE=true`. Defaults to `08_PersonalInfo/`. Override the list with `OBSIDIAN_SEMANTIC_SENSITIVE_PATHS` (comma- or newline-separated folders): ```toml OBSIDIAN_SEMANTIC_SENSITIVE_PATHS = "08_PersonalInfo, 09_Finance" ``` **3. Your own excludes โ€” always denied.** Folders you never want indexed, searched, or read. No unlock flag: ```toml OBSIDIAN_SEMANTIC_EXCLUDE = "03_Journal, Private, Clients/Acme" ``` Which one do you want? - **"Don't index this at all"** โ†’ `OBSIDIAN_SEMANTIC_EXCLUDE` - **"Keep it locked, but I can unlock it with a flag when I need to"** โ†’ `OBSIDIAN_SEMANTIC_SENSITIVE_PATHS` + `OBSIDIAN_SEMANTIC_ALLOW_SENSITIVE` Additional guards: - All paths are resolved through `realpath`. - Path traversal and URL-encoded traversal are blocked. - Symlinks that escape the vault root or point to a denied in-vault path are blocked. > `search_notes` and `read_note` enforce the current exclusion settings on every call. With automatic indexing enabled, the next search also removes excluded stale rows from the index. Confirm the active lists with `index_status`. The local index stores snippets and embedding vectors. Treat it as a derived copy of your vault. See [PRIVACY.md](./PRIVACY.md). ## Indexing Strategy The default is action-driven, not timer-based: 1. The first `search_notes` after server start. 2. The first `search_notes` after a Markdown create, update, delete, or rename event. 3. The first `search_notes` after the embedding model or index format changes; this triggers a full rebuild. 4. An explicit `index_vault` call. The filesystem watcher only marks the index dirty. Indexing runs once, immediately before the next search, and concurrent searches share that work. If recursive watching is unavailable, the server falls back to an incremental scan before every search. Disable automatic indexing with: ```toml OBSIDIAN_SEMANTIC_AUTO_INDEX = "false" ``` Then call `index_vault { "mode": "incremental" }` yourself. The legacy `OBSIDIAN_SEMANTIC_STARTUP_INDEX=true` remains supported, but is not the default because it does work even when no search follows. ## Search Quality Evaluation Create a JSON file containing queries and expected paths to compare keyword, semantic, and hybrid modes under the same conditions: ```json [ { "query": "strong consistency at 1000 TPS", "expected_paths": ["03_Knowledge/QnA/Strong-Consistency-at-1000TPS.md"] } ] ``` ```bash npm run evaluate -- ./queries.json 5 ``` The command reports Recall@K and MRR. Avoid adding ranking complexity or embedding cost unless hybrid search measurably beats the keyword baseline. Refresh the index with `search_notes` or `index_vault` before evaluating. ## Development ```bash npm test npm run pack:check ``` Before publishing: ```bash npm pack --dry-run ``` Confirm the package does not include `data/`, `*.sqlite`, or private vault files. ## License MIT