What is mcp-obsidian?

An Obsidian workspace connector for an AI agent. Obsidian is a Markdown-based note-taking app, and this skill supports vault and note operations plus knowledge of several Obsidian plugin and theme formats.

Use it to read, write, search, tag, move, and manage notes, frontmatter, plugin data, and related vault content.

It gives the agent structured ways to work with notes and vault files instead of guessing how the workspace is organized.

mcp-obsidian — Skill for Claude Code and OpenCode by MichelKerkmeester

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops

agentmods

npx agentmods add skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-obsidian

Made for: Claude Code, 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/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-obsidian/github.svg)](https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-obsidian)

Your own site

<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-obsidian"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-obsidian/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-obsidian"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-obsidian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 13,240 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.13240
Opus 5	$0.00000	$0.06620
Sonnet 5	$0.00000	$0.02648
Haiku 4.5	$0.00000	$0.01324

Measured 6d ago against content hash 0adb4035d1f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

mcp-obsidian scanned grade C with 1 finding 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 6d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (examples/headless-notes-workflow.sh, examples/mcp-roundtrip.sh, examples/official-cli-workflow.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- keywords: obsidian, obsidian vault, notesmd-cli, obsidian-mcp, note management, markdown notes, local rest api, health-md, health data, iconic, icon rules, iconic rulebook, icon automation, file icons, folder icons,

.opencode/skills/mcp-tooling/mcp-obsidian/SKILL.md · 881 lines

How it starts

The opening of the file, as written. The whole thing — 881 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-obsidian Skill

The skill that makes AI use inside Obsidian effective. It operates notes and vaults through three surfaces (headless notesmd-cli, the app-backed official obsidian CLI, and the cyanheads MCP) and knows the twelve plugin and theme file formats at the file layer, so an agent can read, write, search, and extend what the vault contains without guessing.

1. WHEN TO USE

Activation Triggers (explicit user phrases)

"obsidian", "obsidian vault", "notesmd-cli", "obsidian-mcp", "mcp-obsidian"
"note", "notes", "markdown note", "daily note", "vault"
"create a note", "open a note", "search notes", "search my vault"
"add a tag to a note", "manage frontmatter", "delete a note", "move a note"
"obsidian plugin", "make.md", "make-md", "obsidian tables", "brat"
"health", "health data", "apple health", "health chart", "health-md", "health.md"
"iconic", "icons", "icon color", "file icons", "folder icons", "icon rules", "iconic rulebook", "iconic ruleset", "iconic data json", "icon automation"
"local rest api", "obsidian api key"

Automatic Triggers (keyword patterns)

notesmd-cli or obsidian (the CLI binary) appears in the request
obsidian + any action verb (create, open, search, list, print, move, delete, tag)
"vault" in a note-management context
"daily note" or "note frontmatter" in a personal-knowledge context
MCP tool names: obsidian_get_note, obsidian_write_note, obsidian_search_notes

Read the full file on GitHub · 881 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

6d ago Changed 0adb4035d1f0
8d ago First seen · 881 lines · 0 tokens per session scan C 824033d54627

Subscribe to this mod's changes

mcp-obsidian is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 13,240 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Documents Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

mcp-obsidian