広告掲載
MCP.so
ログイン

Obsidian MCP Server

@pmmvr

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

ライセンス

MIT

トランスポート

stdio

作者

pmmvr

Obsidian MCP Server について

MCP server enabling AI agents to perform natural knowledge discovery and analysis across Obsidian vault

#obsidian#mcp-server#knowledge-discovery

Obsidian MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "obsidian-api-mcp-server": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "obsidian-api-mcp-server"
      ]
    }
  }
}

Obsidian MCP Server のツール

16

Text or regex search across note content (optional)

Search type: "text" (default) or "regex"

Limit search to specific folder path

Filter by text in note titles (string, array, or JSON string)

How to match multiple terms: "any" (OR) or "all" (AND)

Filter by tag (string, array, or JSON string - searches frontmatter and inline #tags)

How to match multiple tags: "any" (OR) or "all" (AND)

Amount of content to return (set high for full content)

Boolean to retrieve complete content of all matching notes

Filter by creation date

Filter by modification date

Results per page

Limit matches per note

Directory to browse (defaults to vault root)

Boolean to include files (default: False, folders only for speed)

Boolean to browse all nested directories

概要

What is Obsidian MCP Server?

An MCP server that enables AI agents to perform sophisticated knowledge discovery and analysis across your Obsidian vault through the Local REST API plugin. It is designed for Obsidian users who want AI assistants to query, filter, and retrieve note content for complex, multi-step workflows.

How to use Obsidian MCP Server?

Install via pip or uv (pip install obsidian-api-mcp-server), set the required environment variables (OBSIDIAN_API_URL, optionally OBSIDIAN_API_KEY), and add the server to your MCP client configuration. Run the server with obsidian-mcp. It provides three tools: search_vault, get_note_content, and browse_vault_structure.

Key features of Obsidian MCP Server

  • Advanced search with text, regex, and filter options
  • Retrieve full note content and metadata
  • Browse vault directory structure efficiently
  • Filter by folder, title, tag, and creation/modification dates
  • OR/AND logic for multiple title and tag terms
  • Context length control and pagination for large vaults

Use cases of Obsidian MCP Server

  • Strategic project analysis by retrieving and cross-referencing documentation
  • Meeting action item extraction and chronological tracking
  • Research gap analysis with cross-reference to team expertise
  • Vault structure exploration for quick organizational overview
  • Tag-based knowledge mapping across the entire vault

よくある質問

1

What prerequisites are needed?

Install the Obsidian Local REST API plugin in your vault, enable it, and note the API URL (default: https://localhost:27124) and API key if configured.

2

How do I configure authentication?

Set the `OBSIDIAN_API_KEY` environment variable if you have enabled an API key in the plugin. Avoid hardcoding it into scripts.

3

What tools does the server provide?

Three tools: `search_vault` (advanced search), `get_note_content` (retrieve full note by path), and `browse_vault_structure` (navigate directories).

4

Can I search with regular expressions?

Yes, set `query_type` to `"regex"` in `search_vault`. The server supports regex patterns for complex text matching, such as OR conditions.

5

Is SSL certificate verification disabled?

Yes, the server defaults to HTTPS and disables SSL verification for self-signed certificates. For plain HTTP, use port 27123.

コメント

「メモリとナレッジ」の他のコンテンツ

Semantic Ui React

Semantic-Org

The official Semantic-UI-React integration

13.2K

Orcha

westonhancock

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age

Codebase Memory

DeusData

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

46.7K

Tempreon

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Scento Perfume API (MCP server): free fragrance API, no key

Scento

Scento Perfume API is a free fragrance API and perfume notes database for developers and AI agents. Search 1,500+ perfumes and 400+ ingredients, compare scents, find similar perfumes, map scent families and build occasio

広告掲載