Obsidian SemanticCAUTION
A semantic MCP server for Obsidian that simplifies 20+ tools into 5 AI-optimized operations with intelligent workflow hints and state-aware suggestions.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
🎉 Exciting News! We've taken everything we learned from this project and created something even better! Check out the new **Obsidian MCP Plugin** - a native Obsidian plugin that runs directly inside your vault with improved performance, simplified setup, and enhanced features. We encourage you to try it out!
[](https://www.npmjs.com/package/obsidian-semantic-mcp)
A semantic, AI-optimized MCP server for Obsidian that consolidates 20 tools into 5 intelligent operations with contextual workflow hints.
🚀 Try Our New Native Plugin!
This MCP server taught us valuable lessons about AI integration with Obsidian. We've applied these insights to create the [Obsidian MCP Plugin](https://github.com/aaronsb/obsidian-mcp-plugin), which offers:
- Native Integration: Runs directly inside Obsidian (no external dependencies!)
- Better Performance: Direct vault access without REST API overhead
- Easier Setup: Install like any Obsidian plugin - no API keys or external servers
- Enhanced Features: Full access to Obsidian's internal APIs and search capabilities
- Improved Reliability: No more connection issues or timeouts
👉 [Get the Obsidian MCP Plugin](https://github.com/aaronsb/obsidian-mcp-plugin)
Prerequisites
- Obsidian installed on your computer
- Local REST API plugin installed in your Obsidian vault
- Claude Desktop app
Installation
npm install -g obsidian-semantic-mcp
Or use directly with npx (recommended):
npx obsid
c7eac46409d5OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add obsidian-semantic-mcp --env OBSIDIAN_API_KEY=${OBSIDIAN_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"obsidian-semantic-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"OBSIDIAN_API_KEY": "${OBSIDIAN_API_KEY}"
}
}
}
}Exposed tools (5)
2 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
edit_vault_from_buffer | write | Retry an edit using previously buffered content |
edit_vault_window | write | Edit a portion of a file using fuzzy string matching with automatic fallback strategies |
fetch | read | Fetch and convert web content to markdown |
insert_vault_at_line | write | Insert content at a specific line number |
view_vault_window | read | View a portion of a file with optional search highlighting |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (6)
rejectUnauthorized: false
.prettierrc.json
"OBSIDIAN_API_URL": "https://127.0.0.1:27124",
OBSIDIAN_API_URL=http://127.0.0.1:27123
@modelcontextprotocol/sdk, @types/node, @types/sharp, @types/turndown, axios, dotenv, sharp, turndown
- **Enhanced Features**: Full access to Obsidian's internal APIs and search capabilities
Gates applied: no_behavioural_pass.
c7eac46409d5full audit observations/trust-audit/mcp-server/aaronsb__obsidian-semantic.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | c7eac46409d5 | CAUTION | B | 89 | first audit |
Questions
What is the Obsidian Semantic MCP server?
A semantic MCP server for Obsidian that simplifies 20+ tools into 5 AI-optimized operations with intelligent workflow hints and state-aware suggestions.
What tools does Obsidian Semantic expose?
5 in total: 2 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Obsidian Semantic safe to connect to an agent?
With care. The audit graded it B (89/100) and found 6 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Obsidian Semantic need?
It reads OBSIDIAN_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Obsidian Semantic run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as obsidian-semantic-mcp at 1.7.2.
How current is this page?
The grade is for one exact copy of the source (c7eac46409d5), read on 2026-10-08. The repository is watched and re-audited when it changes.