Obsidian MCP Server

A MCP Server backend for Obsidian. That is what the obsidian mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

This Obsidian plugin runs a local MCP (Model Context Protocol) server, allowing external applications (like AI assistants, scripts, or other tools) to interact with your Obsidian vault through a standardized interface.

• Local MCP Server: — Runs an SSE-based MCP server on a configurable port
• Vault Indexing for Semantic Search: —
• Indexes the content of your Markdown notes into an Orama vector database
• Uses a configurable OpenAI-compatible embedding model (e.g., OpenAI, local Ollama models via compatible endpoints) to generate embeddings
• Allows configuration of text chunking parameters (size, overlap, separators)
• Supports excluding specific files or patterns from indexing using .gitignore syntax

The tools it exposes

The server publishes 9 tools. What each one is for:

• simple_vector_search — Semantic search for notes using vector embeddings
• count_entries — Counts indexed notes and chunks in the Orama database
• list_files — Lists files and folders within a specified directory
• read_file — Reads the content of a specific file
• create_file — Creates a new file
• edit_file — Edits a specific range of lines within an existing file
• delete_file — Deletes a file
• create_folder — Creates a folder
• delete_folder — Deletes a folder

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

How it compares

This 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's toolset — simple_vector_search, count_entries, list_files and 6 more — is a fair guide to whether it matches your workflow. It is maintained by Minhao-Zhang; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Obsidian.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.