Allow an AI to interact with your vault's notes through a self-contained MCP server
If you already use Obsidian MCP Plugin, the obsidian mcp plugin mcp server is the piece that lets your assistant work with it directly. Allow an AI to interact with your vault's notes through a self-contained MCP server.
This Obsidian plugin embeds an MCP (Model Context Protocol) server directly within Obsidian, providing a streamlined way for applications to interact with your vault.
The server ships on npm as pnpm, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
obsidian-mcp-read-file — Get file contentsobsidian-mcp-diff-edit-file — Edit files using simplified udiff (see below)obsidian-mcp-search-contents — Fuzzy search across the contents of all files in your vaultobsidian-mcp-search-filenames — Fuzzy search across all file names in your vaultobsidian-mcp-list-files — List files and directories in your vault with customizable depth and result limitsobsidian-mcp-upsert-file — Create or update filesobsidian-mcp-rollback-edit — Roll back the last edit to a markdown file (reverts the last change made by supported tools)Schemas — Each schema has two sections: 1. metadata Defines file naming and storage details 2. fields Defines the structure of your data (used to generate thePrerequisites — A nix flake is provided to create a standardized development environmentThis sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Obsidian MCP Plugin's toolset — obsidian-mcp-read-file, obsidian-mcp-diff-edit-file, obsidian-mcp-search-contents and 6 more — is a fair guide to whether it matches your workflow. It is maintained by jlevere; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Obsidian MCP Plugin's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| obsidian-mcp-read-file | Get file contents |
| obsidian-mcp-diff-edit-file | Edit files using simplified udiff (see [below](#obsidian-mcp-diff-edit-file)) |
| obsidian-mcp-search-contents | Fuzzy search across the contents of all files in your vault |
| obsidian-mcp-search-filenames | Fuzzy search across all file names in your vault |
| obsidian-mcp-list-files | List files and directories in your vault with customizable depth and result limits |
| obsidian-mcp-upsert-file | Create or update files |
| obsidian-mcp-rollback-edit | Roll back the last edit to a markdown file (reverts the last change made by supported tools) |
| Schemas | Each schema has two sections: 1. metadata Defines file naming and storage details 2. fields Defines the structure of your data (used to generate the Zod tool) |
| Prerequisites | A nix flake is provided to create a standardized development environment. |
{
"mcpServers": {
"obsidian": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:<your_server_port>/sse"]
}
}
}Configuration as documented by the project. Restart the client after saving.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.