MCPVault is a local Model Context Protocol server that lets compatible AI clients read, search, and edit notes stored in an Obsidian vault. It is for users who want coding agents and other supported clients to work with their vault while restricting file access to its configured root. The catalogue entries provide add-ons for using MCPVault with AI coding agents.
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.
npx agentmods add skills/bitbonsai/mcpvault/obsidiannpx skills add bitbonsai/mcpvault --skill obsidiangit clone --depth 1 https://github.com/bitbonsai/mcpvaultWrote 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/skills/bitbonsai/mcpvault/obsidian)<a href="https://agentmods.dev/skills/bitbonsai/mcpvault/obsidian"><img src="https://agentmods.dev/badge/skills/bitbonsai/mcpvault/obsidian.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.02828 |
| Opus 5 | $0.00024 | $0.01414 |
| Sonnet 5 | $0.00010 | $0.00566 |
| Haiku 4.5 | $0.00005 | $0.00283 |
Grade A, and why
obsidian 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 6d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Skill
Routing Policy
Use the backend that best matches user intent:
-
MCP (default for vault data operations)
- Read/write/patch/search notes
- Move/rename notes with
move_note, then explicitly repair backlinks - Frontmatter and tag updates
- Metadata and batch note operations
-
Obsidian CLI/App context (only when app context is needed)
- Open a note in Obsidian from URI
- Trigger app/plugin workflows that MCP cannot perform
-
CLI git (sync/backup workflows)
- Initialize repo, configure remote, commit, pull, push
- Periodic or manual vault backup/sync requests
When a request is ambiguous, pick MCP first unless the user explicitly asks for sync/backup/git/app behavior.
Safe Note Rename Workflow
Use MCP move_note for every note move or rename, even when Obsidian is running. Do not invoke the Obsidian CLI move command automatically: delayed link rewrites can apply stale byte offsets to notes edited after the move began, silently corrupting unrelated content (#176). Reconsider CLI moves only after an upstream fix has been independently retested.
Backlink preservation is an explicit, verifiable second step:
- Before moving, search for the old wikilink target using both its vault-relative path and filename without the extension. If Obsidian is running, its read-only
backlinkscommand may supplement discovery, but it does not replace the MCP search. - Move the note with MCP
move_note. - Read each referring note and patch only exact wikilink targets, including embeds and links with aliases or fragments. Preserve display text (
|alias) and#heading/#^block-idsuffixes while changing the target. - Search again for the old path and basename. Report any remaining references instead of claiming success.
search_notesreturns at most 20 results. If a search reaches that cap, or the old basename is ambiguous, tell the user exhaustive backlink repair cannot be proven and ask before continuing with a broader scan.
What ships with it
3 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.
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 First seen · 205 lines · 48 tokens per session scan A 98a9ed3599e7
obsidian is a skill published in the GitHub repository bitbonsai/mcpvault (1,645 stars, last pushed 5d ago), licensed MIT. It adds 48 tokens to every session and 2,828 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.