obsidian_mcp
Enables reading, writing, searching, and managing Obsidian vault notes through MCP tools and prompts, allowing AI agents to interact with local knowledge bases.
README
Obsidian MCP Server
Have been using obsidian for quite awhile (have years and years of notes in my vault(have years and years of notes in my vault(have years and years of notes in my vault(have years and years of notes in my vault(have years and years of notes in my vault(have years and years of notes in my vault(have years and years of notes in my vault(have years and years of notes in my vault(have years and years of notes in my vault) and thought we could benefit from some kind of MCP server.
This can be used to read notes from your vault, have AI agents create notes, etc.
Will periodically add more tools and enhancements to this...
Note: This is meant to be used locally or hosted yourself for now. This MCP server currently does not come with an AKS deployment or anything like that. Your vault should ideally also be local (unless you're using some weird plugin), so don't see this as a serious downside.
Setup
Install dependencies
Requires uv. Clone the repo, then:
# Install runtime dependencies
uv sync -p $(cat ./.python-version)
# Install with test extras
uv sync --extra test
# Install with dev extras
uv sync --extra dev
# Run tests
uv run pytest
# Run the server directly
uv run python -m obsidian_mcp.main
The virtual environment is created automatically by uv inside .venv/. Use .venv/bin/python as the interpreter path in your MCP client config.
MCP client config
{
"mcpServers":{
"obsidian_mcp":{
"command":"/<path_to_project>/.venv/bin/python",
"args": ["-m", "obsidian_mcp.main"],
"env":{
"OBSIDIAN_VAULT__PATH": "<local vault path>",
"OBSIDIAN_LOGGING__LEVEL": "INFO",
"OBSIDIAN_LOGGING__FORMAT": "%(asctime)s | %(levelname)-8s | %(name)s | %(message)s",
"OBSIDIAN_SERVER__HOST": "127.0.0.1",
"OBSIDIAN_SERVER__PORT": 8000,
"OBSIDIAN_VAULT__ENABLE_WIKILINKS": "True",
"OBSIDIAN_VAULT__ENABLE_FRONTMATTER": "True",
"OBSIDIAN_SEARCH__ENABLED": "True",
"OBSIDIAN_SEARCH__MAX_RESULTS": 100
}
}
}
}
Note: If you have <project_dir>/.env file populated. You can remove these entries in the mcp config. The config class should load the
.env.
Tools
| Tool | Description |
|---|---|
list_notes |
List all notes in the vault or a subdirectory. Optionally exclude .obsidian/ and .trash/ (both excluded by default). |
get_note |
Read a note by its vault-relative path. Returns path, title, tags, frontmatter, and body. |
search_notes |
Search notes for a literal query string. Supports case sensitivity, frontmatter inclusion, and excluding .obsidian//.trash/. |
create_note |
Create a new note at a given vault-relative path with optional YAML frontmatter. |
append_to_note |
Append text to the end of an existing note without overwriting it. |
update_note |
Overwrite the body of an existing note, optionally replacing its frontmatter. |
get_links |
Return all outgoing wikilink targets from a note's body. |
get_backlinks |
Return all notes in the vault that contain a wikilink pointing to the given note. |
Prompts
| Prompt | Description |
|---|---|
summarize_note |
Fetches a note by path and returns a structured prompt asking the LLM for a TL;DR, key-point bullets, and any action items or decisions. |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.