Obsidian Vault Search

Enables Claude to search Obsidian vault contents with ripgrep, including frontmatter, headings, and links.
  • python

3

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "kpetrovsky-kp-ripgrep-mcp": {
      "command": "python",
      "args": [
        "-m",
        "rgrep_mcp.server"
      ],
      "env": {
        "OBSIDIAN_VAULT_PATH": "/path/to/your/obsidian/vault"
      }
    }
  }
}

This MCP server lets Claude search your Obsidian vault contents using ripgrep, with intelligent Obsidian-specific context such as frontmatter, wiki links, and headings. It helps you rapidly locate information, analyze links, and understand how notes connect within your vault.

How to use

Install and run the MCP server, then connect Claude to it as an MCP client. You can search across all notes or limit scope to content, frontmatter, or specific folders. Claude will return results with smart context showing where matches occur (which frontmatter property or which heading). Use it to find where a topic appears, inspect links, and explore how notes reference each other.

How to install

Prerequisites you need before starting:

  • Python 3.8 or higher

  • ripgrep installed and available in PATH

  • An Obsidian vault you want to search

Install ripgrep on your platform if you haven’t already.

Clone the MCP server package and install it in editable mode.

  • Clone the MCP repository

  • Install the package

Clone the repository and install the MCP server package locally.

Configuration and usage with Claude

{
  "mcpServers": {
    "obsidian-search": {
      "command": "python",
      "args": ["-m", "rgrep_mcp.server"],
      "env": {
        "OBSIDIAN_VAULT_PATH": "/path/to/your/obsidian/vault"
      }
    }
  }
}

Alternative configuration

If you prefer environment variables or a local config file, you can set the vault path with an environment variable or create a local JSON config file.

# Environment variable (all platforms)
export OBSIDIAN_VAULT_PATH="/path/to/your/obsidian/vault"
{
  "vault_path": "/path/to/your/obsidian/vault",
  "default_case_sensitive": false,
  "default_result_limit": 15
}

Troubleshooting

If Claude cannot start or find the vault, verify the vault path, environment variable, and ripgrep availability. Ensure you are pointing to an actual Obsidian vault directory that contains Markdown files.

Common issues and fixes include verifying ripgrep is installed, ensuring the OBSIDIAN_VAULT_PATH points to the vault, and using absolute paths. If you encounter permission prompts, grant Claude access to the vault directory on your operating system.

Example usage

Ask Claude to search for a term across your vault or within a specific folder, view results with context, and inspect how notes link to each other.

Available tools

rg_search_notes

Search text content within notes with flexible scope options and smart context. You can search all content, only frontmatter, or only note content, and you’ll get context showing which frontmatter property or heading contains each match. You can filter by folder and control result limits.

rg_search_links

Find and analyze links across your vault, including wiki links, markdown links, and external URLs. Filter by URL patterns or title patterns to identify broken links or map knowledge graph connections.

rg_search_backlinks

Find all notes that link to a specific target note. Understand the context around each backlink and how ideas connect across your vault.

rg_search_recent_notes

Find notes modified within specific date ranges. Use YYYY-MM-DD format, and combine with other searches to locate recent notes on topics of interest.

rg_search_orphaned_notes

Identify notes with no incoming or outgoing links to improve vault integration and organization.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational