Obsidian Publish

Obsidian Publish MCP Connector for Claude

A+

Empower your AI to read your public or private Obsidian Publish sites. Index files, crawl navigation trees, and retrieve deep markdown knowledge.

5 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Obsidian Publish environment to your AI agent and construct an intelligent oracle that reads smoothly from your personal or corporate markdown knowledge base.

What you can do

  • Vault Crawling — Programmatically fetch your entire published vault structure utilizing list_files and list_navigation to build contextual trees.
  • Direct Note Access — Execute get_file to stream the complete raw markdown contents of any note directly into your chat workflow for fast summarization.
  • Metadata Operations — Use get_metadata to retrieve frontmatter properties, tags, and internal link logic mapped by Obsidian.
  • Site Auditing — Easily ping site_info to ensure connectivity and verify the deployment status of your target Obsidian publish endpoint.

How it works

  1. Subscribe to this server
  2. Enter your Obsidian Publish Site ID (and optional access token for private vaults)
  3. Start fetching and analyzing your personal notes directly from Claude, Cursor, or any MCP client

Who is this for?

  • Researchers & Writers — seamlessly command an AI to read past chapters, cross-reference characters, or verify published assertions without opening Obsidian.
  • Corporate Teams — build a highly accessible chatbot that rapidly reads and summarizes your team's documented standard operating procedures (SOPs).
  • Developers — fetch specific code snippets and technical architectures housed in your digital garden natively within the IDE.
markdownvault-indexingstatic-siteknowledge-basenote-takingweb-publishing

5 tools expose this connector's capabilities to your AI agent.

list_files

List all explicitly published raw file paths across the Obsidian workspace

get_file

Retrieve exact textual file content and binary assets

site_info

Identify global configuration and styling mapping the site

list_navigation

Visualize structurally formatted Markdown navigation trees

get_metadata

Extract internal creation hashes mapping a specific Markdown page

See how to talk to your AI agent using Obsidian Publish.

Check the vault and list all the files currently publicly available.

According to the navigation tree, you have 14 distinct markdown entries published. Key documents include 'Index', 'Machine Learning Setup', and 'Project Specs'.

Read the contents of 'System Requirements 2026.md'.

I've pulled the content of 'System Requirements 2026.md'. The document includes heavy focus on horizontal scaling algorithms and Python-centric deployments. Would you like a condensed executive summary?

Fetch the metadata and tags applied to my 'Inbox' note.

The 'Inbox' note has the following metadata: generated on May 5th, tagged with `#todo` and `#ideas`, and links heavily to `Projects.md` and `Archived Content.md`.

Yes. When the model invokes `list_navigation`, it downloads the systematic JSON map of the entire public vault, thereby allowing it to understand the relationships and physical structure of your folders perfectly.

Related Connectors