Obsidian-MCP AGENTS.md

Obsidian-MCP AGENTS.md is an instructions file for Codex, OpenCode from Kynlos/Obsidian-MCP. It costs 4,816 tokens per session, scanned A, original, MIT.

A set of instructions for using Obsidian-MCP, a connection that lets an AI assistant work with notes in an Obsidian vault, which is a folder of linked Markdown notes.

In plain words
What is it for?
Saving code snippets, architecture notes, knowledge notes, and conversation summaries; searching or organizing an Obsidian vault; and checking vault statistics.
Why use it?
It tells the assistant when and how to save, find, update, organize, and export notes, so coding discussions and documentation do not have to be managed manually.

Instructions file for CodexOpenCode

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/kynlos/obsidian-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/Kynlos/Obsidian-MCP

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.

agentmods badge for Obsidian-MCP AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kynlos/obsidian-mcp/agents-md.svg)](https://agentmods.dev/instructions/kynlos/obsidian-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kynlos/obsidian-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kynlos/obsidian-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,816 This file is loaded in full into every session.
When invoked 4,816 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5 $0.04816 $0.04816
Opus 5 $0.02408 $0.02408
Sonnet 5 $0.00963 $0.00963
Haiku 4.5 $0.00482 $0.00482

Measured 5d ago against content hash 09ee72004cdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Obsidian-MCP 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.

AGENTS.md · 970 lines

How it starts

The opening of the file, as written. The whole thing — 970 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Obsidian MCP Guide for AI Assistants

This file explains the Obsidian MCP for AI coding agents and assistants

What is This MCP?

The Obsidian MCP is a Model Context Protocol server that connects AI assistants (like Amp) to Obsidian vaults, enabling AI-powered note creation, management, and organization.

Purpose: Allow AI agents to create, read, update, and organize notes in Obsidian vaults automatically during coding sessions.

Total Tools: 61 comprehensive note management tools


Quick Reference

When to Use This MCP

Good use cases:

  • User asks to "save this to Obsidian"
  • User wants to document code or architecture
  • User asks to "create a note about X"
  • User wants to save code snippets for later
  • User asks to organize or search their notes
  • User wants to export documentation
  • User requests vault statistics or analytics

Don't use for:

  • General file operations (use Read, create_file instead)
  • Git operations (use Bash tool)
  • Code execution or testing

Most Common Tools

Create Notes:

  • save_code_snippet - Save code with syntax highlighting
  • save_knowledge_note - Create general notes
  • save_thread_summary - Archive AI conversations

Read & Search:

  • list_notes - Browse vault
  • read_note - Get note content
  • search_notes - Find notes by content/tags

Export:

  • export_vault_pdf - Beautiful PDF with table of contents
  • export_note_pdf - Single note as PDF

Complete Tool Reference

📝 Note Creation (4 tools)

save_code_snippet

Save code with metadata, syntax highlighting, and tags.

{
  title: "Binary Search Algorithm",
  code: "function binarySearch(arr, target) {...}",
  language: "javascript",
  description: "Efficient search algorithm",
  tags: ["algorithms", "search", "javascript"]
}

When to use: User shares code they want to save for later reference.

save_thread_summary

Archive AI conversation with key insights and code snippets.

Read the full file on GitHub · 970 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.

  1. 5d ago First seen · 970 lines · 4,816 tokens per session scan A 09ee72004cdc

Subscribe to this mod's changes

Obsidian-MCP AGENTS.md is an instructions file published in the GitHub repository Kynlos/Obsidian-MCP (8 stars, last pushed 9mo ago), licensed MIT. It adds 4,816 tokens to every session, about $0.0241 per session on Opus 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 2026-08-31.