Borrowing it
Nothing to install: this file belongs to smith-and-web/obsidian-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/smith-and-web/obsidian-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/smith-and-web/obsidian-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/smith-and-web/obsidian-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/smith-and-web/obsidian-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/smith-and-web/obsidian-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/smith-and-web/obsidian-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/smith-and-web/obsidian-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01459 | $0.01459 |
| Opus 5.5 | $0.00584 | $0.00584 |
| Sonnet 5.5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
obsidian-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian MCP Server — Project Conventions
A Model Context Protocol server that lets AI assistants interact with an Obsidian vault (notes, frontmatter, tags, search, links) over an SSE transport.
Stack
- Language: TypeScript 5.x, ES modules (
"type": "module"). Useimport/export, neverrequire. - Runtime: Node.js >= 20.19. Build target is
dist/viatsc. - HTTP: Express 5.
- MCP:
@modelcontextprotocol/sdk. - Frontmatter:
gray-matter. - Tests: Vitest. Lint: ESLint + Prettier (Prettier rules are enforced through ESLint).
Commands
| Task | Command |
|---|---|
| Install | npm install |
| Build | npm run build (tsc → dist/) |
| Dev server (watch) | npm run dev |
| Test | npm test (vitest run) |
| Test (watch) | npm run test:watch |
| Lint | npm run lint (eslint src/) |
| Auto-fix lint/format | npm run lint:fix then npm run format |
| Format check | npm run format:check |
Always run npm test and npm run lint before opening a PR — both must pass clean.
Prettier violations surface as ESLint errors, so npm run lint:fix resolves most formatting issues.
Layout
src/
├── index.ts # Express server entrypoint & wiring
├── server/
│ ├── mcp.ts # MCP protocol handling (SSE connection, message routing)
│ └── middleware.ts # Express middleware (auth, etc.)
├── tools/
│ ├── definitions.ts # Tool schemas (JSON Schema inputSchema)
│ ├── handlers.ts # Tool execution → dispatches to VaultManager
│ └── index.ts # Re-exports
├── vault/
│ ├── VaultManager.ts # Core vault operations (the real logic lives here)
│ └── frontmatter.ts # YAML frontmatter utilities (gray-matter)
├── index/ # Optional semantic search (pgvector + Ollama); gated on DATABASE_URL
│ ├── config.ts # Env → IndexConfig (null when DATABASE_URL unset)
│ ├── exclusions.ts # Paths the indexer never reads (tested)
│ ├── chunker.ts # Heading-aware chunking (tested, pure)
│ ├── embedder.ts # Ollama client + FakeEmbedder for tests
│ ├── ranking.ts # Configurable fusion, weights and per-note cap
│ ├── store.ts # All SQL: schema, upserts, hybrid search
│ ├── scanner.ts # Vault walk, change detection, one reconcile pass
│ └── SearchService.ts # What the tools call
├── maintain/ # Maintenance configuration, decisions, reports and worker
├── maintain.ts # Report-only maintenance CLI
├── learn/ # Learn log, redaction, configuration and report assembly
├── learn-report.ts # Read-only learn-report CLI entrypoint
├── eval/ # Golden schema, metrics and ranking grid
├── eval.ts # Read-only brain-eval CLI entrypoint
├── indexer.ts # Indexer entrypoint (same image, second container)
└── types/
└── index.ts # Shared types
sql/001_schema.sql # Index DDL; __DIM__ substituted at start
sql/002_learning.sql # Learn log DDL; applied even when logging is disabled
sql/003_maintenance.sql # Additive maintenance schema; history and decisions
tests/ # Vitest specs (*.test.js) — mirror the src module under test
examples/test-vault/ # Sample vault used by examples and manual testing
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago Changed · +6 lines · +116 tokens per session c6e2bdc7664a
- 14d ago Changed · +3 lines · +48 tokens per session bd8ac1a1a91c
- 22d ago Changed · +1 lines · +50 tokens per session f9b6acd96920
- 23d ago Changed · +15 lines · +298 tokens per session f7e0c8e9ea1d
- 2mo ago First seen · 86 lines · 947 tokens per session scan A 557962de286f
obsidian-mcp-server CLAUDE.md is an instructions file published in the GitHub repository smith-and-web/obsidian-mcp-server (19 stars, last pushed 4d ago), licensed MIT. It adds 1,459 tokens to every session, about $0.0058 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
obsidian-mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| obsidian-mcp-server CLAUDE.mdsmith-and-web/obsidian-mcp-server | Instructions file | 19 | 4d ago | MIT | A | 1,459 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |