What is obsidian-mcp-server AGENTS.md?

Project instructions for an Obsidian MCP server, a program that lets Claude search and read notes stored in Obsidian vaults. They also describe the project's issue-tracking workflow and internal communication design.

Use them when working on this Obsidian MCP server, especially when handling vault access, JSON-RPC messages, callable tools, multiple vaults, or Beads issues.

They give an agent the project context it needs before changing code, including how the server communicates and how work is tracked. This reduces misunderstandings about the architecture and workflow.

obsidian-mcp-server AGENTS.md — Instructions file for Codex and OpenCode by frstlvl: Project instructions for an Obsidian MCP server, a prog

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/frstlvl/obsidian-mcp-server/agents-md

Clone the repo

git clone --depth 1 https://github.com/frstlvl/obsidian-mcp-server

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/frstlvl/obsidian-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/frstlvl/obsidian-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/frstlvl/obsidian-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/frstlvl/obsidian-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 5,196 This file is loaded in full into every session.

When invoked 5,196 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin 89% copy Near-identical to another mod in the catalogue.

Token cost

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	$0.05196	$0.05196
Opus 5	$0.02598	$0.02598
Sonnet 5	$0.01039	$0.01039
Haiku 4.5	$0.00520	$0.00520

Measured 5d ago against content hash c7b4b9077d3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

obsidian-mcp-server AGENTS.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 5d 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.

Origin

This is a copy

89% identical to obsidian-mcp-server copilot-instructions.md — 125 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 754 lines

How it starts

The opening of the file, as written. The whole thing — 754 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obsidian MCP Server - AI Instructions

Project Overview

This is a Model Context Protocol (MCP) server that provides real-time Claude AI access to Obsidian vaults. The server enables dynamic querying, searching, and reading of notes without token limitations through JSON-RPC 2.0 over stdio.

Key Purpose: Bridge Claude AI with Obsidian knowledge bases through efficient, secure, real-time vault access.

Issue Tracking

This project uses bd (beads) for issue tracking. Run bd prime for workflow context, or install hooks (bd hooks install) for auto-injection.

Quick reference:

bd ready - Find unblocked work
bd create "Title" --description "Description" --type task --priority 2 - Create issue
bd close <id> - Complete work
bd sync - Sync with git (run at session end)

For full workflow details: bd prime

Critical Project Context

MCP Architecture (CRITICAL)

Protocol: JSON-RPC 2.0 over stdio (stdin/stdout), NOT REST/HTTP
Server Model: Long-running process with structured message communication
Resources: Vault notes exposed as obsidian://vault/[path] URIs
Tools: Functions callable by Claude (list_vaults, search_vault, create_note, etc.)
Multi-Vault: Single server instance serving multiple vaults via vaults config array
Implementation: TypeScript using @modelcontextprotocol/sdk

Technology Stack

Runtime & Build:

Node.js 18+ (recommended 20+)
TypeScript 5.7+ with strict mode
ES Modules (type: "module" in package.json)

Core Dependencies:

@modelcontextprotocol/sdk - MCP protocol implementation
@xenova/transformers - Local embedding generation (Transformers.js)
vectra - Local vector database for semantic search
chokidar - File system watcher for automatic index updates
winston - Structured logging system
gray-matter - YAML frontmatter parsing
zod - Runtime type validation

Development:

tsx - TypeScript execution and hot reload
prettier - Code formatting
eslint - Code linting

Read the full file on GitHub · 754 lines

Changes

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.

5d ago First seen · 754 lines · 5,196 tokens per session scan A c7b4b9077d3f

Subscribe to this mod's changes

obsidian-mcp-server AGENTS.md is an instructions file published in the GitHub repository frstlvl/obsidian-mcp-server (1 stars, last pushed 4mo ago), licensed MIT. It adds 5,196 tokens to every session, about $0.0260 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to obsidian-mcp-server copilot-instructions.md, differing in 125 lines, and is treated as a copy.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

obsidian-mcp-server AGENTS.md