This server enables read-only semantic retrieval for Obsidian vaults, allowing agents to search, read, and manage a local index without modifying notes.
Search: Perform hybrid, semantic, or keyword searches across your notes, with options to filter by folder, include archived notes, set result limits, and access sensitive paths if permitted.
Read notes: Retrieve full note content or specific line ranges by vault-relative path, with optional access to sensitive paths.
Index management: Build or update the semantic index incrementally or fully, target specific files, preview changes via dry-run, and check index status and safety settings.
Safety controls: Exclude sensitive or archived folders by default, respect custom exclusion lists, and unlock protected content only via a server-side environment variable.
Local-first: Uses Ollama embeddings and stores the index in SQLite, ensuring all data remains on your machine. The index updates automatically when needed (e.g., after file changes).
Read-only: Provides strictly read access; no modifications, edits, or deletions are possible. Works directly from the filesystem, with no Obsidian app required.
Provides read-only semantic search and retrieval over Obsidian vaults, enabling agents to find and read notes without modifying the vault.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Obsidian Semantic Search MCP find the note on Redis Lua atomicity"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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:
local Obsidian vault -> read-only scanner -> local SQLite index -> MCP search/read toolsNo note writes. No cloud embeddings by default. No Obsidian plugin runtime. No sync service.
Status:
0.3.1early preview. The server is usable today, but ranking behavior and tool schemas may change before1.0.
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:
{
"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"
}
]
}Related MCP server: second-brain-mcp
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:
ollama pull bge-m3
curl http://localhost:11434/api/tagsPrint setup guidance:
npx -y --package @dalecb/obsidian-semantic-mcp obsidian-semantic-mcp-setupAdd this to ~/.codex/config.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:
obsidian_semantic.index_status
obsidian_semantic.search_notes { "query": "Redis Lua atomicity", "limit": 5 }Add the server at user scope so the personal vault path stays out of project .mcp.json files:
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_semanticStart 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 for scope and command details.
In Claude Desktop, open Settings → Developer → 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:
{
"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 for Claude Desktop configuration and logs.
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 — 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 — restructures content |
Obsidian must run | No — reads files directly | Yes — 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.
index_statusReturns index metadata and safety settings.
index_vaultBuilds or updates the external SQLite index.
{ "mode": "incremental" }Specific files:
{
"mode": "incremental",
"paths": ["02_Projects/My Note.md"]
}search_notesSearches notes with hybrid semantic and keyword ranking.
{
"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_noteReads a note or line range by vault-relative path.
{
"path": "02_Projects/My Note.md",
"start_line": 10,
"end_line": 40
}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 resultsDefault storage:
~/.obsidian-semantic-mcp/
data/semantic.sqliteThe vault remains the source of truth. The SQLite database is a derived index and can be deleted/rebuilt.
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 — 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):
OBSIDIAN_SEMANTIC_SENSITIVE_PATHS = "08_PersonalInfo, 09_Finance"3. Your own excludes — always denied. Folders you never want indexed, searched, or read. No unlock flag:
OBSIDIAN_SEMANTIC_EXCLUDE = "03_Journal, Private, Clients/Acme"Which one do you want?
"Don't index this at all" → OBSIDIAN_SEMANTIC_EXCLUDE
"Keep it locked, but I can unlock it with a flag when I need to" → 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_notesandread_noteenforce 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 withindex_status.
The local index stores snippets and embedding vectors. Treat it as a derived copy of your vault. See PRIVACY.md.
The default is action-driven, not timer-based:
The first search_notes after server start.
The first search_notes after a Markdown create, update, delete, or rename event.
The first search_notes after the embedding model or index format changes; this triggers a full rebuild.
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:
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.
Create a JSON file containing queries and expected paths to compare keyword, semantic, and hybrid modes under the same conditions:
[
{ "query": "strong consistency at 1000 TPS", "expected_paths": ["03_Knowledge/QnA/Strong-Consistency-at-1000TPS.md"] }
]npm run evaluate -- ./queries.json 5The 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.
npm test
npm run pack:checkBefore publishing:
npm pack --dry-runConfirm the package does not include data/, *.sqlite, or private vault files.
MIT
Return semantic index status and safety settings.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It explicitly states a read-only operation ('Return'), which is transparent. However, it does not disclose error conditions or authentication needs, but for a simple parameterless status check, the clarity is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It is front-loaded and concise, earning its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the purpose is clear, the description does not elaborate on the return value's structure or content. Since there is no output schema, more specificity about what 'status and safety settings' includes would be beneficial for a complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are 0 parameters, so per guidelines the baseline is 4. No additional parameter info is needed, and the schema coverage is trivially 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Return') and resource ('semantic index status and safety settings'), clearly distinguishing it from sibling tools like search_notes and index_vault, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites, when-not-to-use, or contrast with sibling tools like index_vault.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Index or reindex the Obsidian vault into the external semantic index. Does not modify the vault.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | incremental | |
| paths | No | ||
| dry_run | No | ||
| include_sensitive | No | Requires OBSIDIAN_SEMANTIC_ALLOW_SENSITIVE=true on the server. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It states the tool does not modify the vault, which is helpful. However, it fails to disclose behaviors such as the effect of dry_run, what happens on reindex, or prerequisites like requiring the vault to be open. Partial disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences with no unnecessary words. It front-loads the core action and a key safety note. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 4 parameters, no output schema, and no annotations, the description lacks completeness. The agent is not informed about the behavior of mode (incremental vs full), paths (what happens if omitted), dry_run effects, or the requirement for include_sensitive. More details are needed for safe and effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low (25%), with only include_sensitive having a description. The tool description adds no information about any parameter semantics, leaving the agent to infer meaning from names only. This is insufficient for 4 parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Index or reindex' and the resource 'Obsidian vault into the external semantic index'. It distinguishes from sibling tools like search_notes, read_note, and index_status by describing a unique operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for creating or updating the semantic index, and states it does not modify the vault, but lacks explicit guidance on when to use this tool versus alternatives like search_notes or index_status. No exclusions or conditions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read-only markdown note reader by vault-relative path and optional line range.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| end_line | No | ||
| start_line | No | ||
| include_sensitive | No | Requires OBSIDIAN_SEMANTIC_ALLOW_SENSITIVE=true on the server. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description declares 'Read-only' which indicates no mutations, but it lacks details on error handling, behavior for invalid paths, line range specifics, and does not mention the 'include_sensitive' parameter or its implications. With no annotations, the description should provide more behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with 11 words, no redundancy. Front-loaded with the key action and resource type. Every component is necessary and adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is present, so the description should hint at the return value (e.g., note content). It does not. Also missing details on line range boundaries, path formatting, and the 'include_sensitive' parameter. Given tool complexity (4 params, no output schema), more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning to three parameters not documented in the schema: 'path' (vault-relative path), 'start_line' and 'end_line' (optional line range). Schema coverage is low (25%), and the description compensates by clarifying the core parameters, though it does not explain 'include_sensitive' beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it reads markdown notes by vault-relative path with an optional line range. It uses specific verb 'read' and resource 'markdown note', distinguishing it from sibling tools like search_notes (search) and index_vault (index).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you know the vault-relative path and optionally want a line range, but it does not explicitly compare with siblings or state when not to use this tool. No exclusions or alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read-only hybrid semantic/keyword search over the Obsidian vault. Returns file-level results with matched sections.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | hybrid | |
| limit | No | ||
| query | Yes | ||
| folder_exclude | No | ||
| folder_include | No | ||
| include_archived | No | ||
| include_sensitive | No | Requires OBSIDIAN_SEMANTIC_ALLOW_SENSITIVE=true on the server. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only states 'read-only' but does not disclose behavioral traits like required authentication, rate limits, or consequences of the search. With no annotations, the description carries full burden, yet it is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise with two sentences, no redundancy, and front-loaded key information. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (7 parameters, hybrid search, no output schema), the description is too brief. It lacks details on result format, pagination, mode semantics, and relationship to indexing status.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 14% (one parameter documented). The description does not add meaning to the 7 parameters, such as explaining folder_exclude, folder_include, or the effect of include_archived. The mode enum is not elaborated.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is a read-only hybrid semantic/keyword search over the Obsidian vault, returning file-level results with matched sections. This distinguishes it from siblings like read_note (reading a specific note) and index_vault (indexing).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, when not to use it, or how to choose between modes (hybrid, semantic, keyword). The agent must infer usage from context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.2.1index_statusindex_vaultread_notesearch_notesEach tool has a clearly distinct purpose: searching, reading, indexing, and checking index status. No overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern in snake_case, e.g., search_notes, read_note, index_vault, index_status.
Four tools is well-scoped for a read-only semantic search server, covering search, reading, indexing, and status without redundancy.
Core workflow is covered: search, read, index, status. Minor gaps like missing file listing or vault navigation, but these are not essential for the stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Read-only search of your Sortio knowledge graph (files and entities) for Claude and ChatGPT.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Search your Obsidian vault to quickly find notes by title or keyword, summarize related content, a…
Read-only semantic search over Vedic scripture verses, commentaries, and recorded lectures.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/DalecB/obsidian-semantic-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
