Obsidian_fetch

Name: Obsidian_fetch
Author: soukouki

by soukouki

MCP servers focused on fetching and presenting information from Obsidian vaults.

2 4 tools GitHub

No known CVEs

MIT license

Maintained

Last commit 43d ago

Works with most clients

Transport: stdio, http

4 tools · ~128 tok

Grade A · 0.1% of 200K ctx

Edit this pageView history

Productivity

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "obsidian-fetch": {
      "command": "<see-readme>",
      "args": []
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/obsidian-fetch)](https://mcppedia.org/s/obsidian-fetch)

Read me

What Obsidian_fetch does

MCP servers focused on fetching and presenting information from Obsidian vaults.

Test This Server

This server supports HTTP transport. Be the first to test it — help the community know if it works.

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

64/100across 5 weighted dimensions

How we score →

0255075100

−36

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

No package registry to scan.

Inventory

Tools (4)

Click any tool to inspect its schema.

~128 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Obsidian_fetch safe to use?: Obsidian_fetch has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.
How do I install Obsidian_fetch?: Obsidian_fetch can be installed by cloning its GitHub repository and following the setup instructions in the README.
What can Obsidian_fetch do?: Obsidian_fetch provides 4 tools: Installation, Usage, Contributing, License. See the full tools list on the server page for descriptions and parameters.
What AI clients work with Obsidian_fetch?: Obsidian_fetch is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.
Is Obsidian_fetch actively maintained?: Obsidian_fetch is recently maintained — last commit was 43 days ago. It has 2 GitHub stars.

Similar servers

Others in productivity

View all →

Sequential Thinking MCP Server98

Dynamic problem-solving through sequential thought chains

87.9k 1

Memory MCP Server96

Persistent memory using a knowledge graph

87.9k 5

Qmd95

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

27.3k 4

Notion Mcp Server94

Official Notion MCP Server

4.5k 7

MCP Security Weekly

Get CVE alerts and security updates for Obsidian_fetch and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

ObsidianFetch

MCP servers focused on fetching and presenting information from Obsidian vaults.

The existing MCP server has the following drawbacks:

It supports many commands, which can cause slow prompt loading when computational resources are limited.

When reading a note labeled "Sample Note", it is necessary to search for its path first before loading it, but the LLM may not always follow this procedure.

Some tools include unnecessary options, leading the LLM to sometimes fail to invoke them correctly.

These issues become particularly noticeable when running an LLM on a local GPU.
To address this, we developed a new MCP server that simply retrieves and loads lists of notes.

The new server also provides the following additional features:

When the LLM attempts to retrieve link information by searching with brackets like [[link name]], the server automatically removes any characters that cannot be used in links.

In addition to loading the note contents, it also displays backlinks—notes that link to the currently opened note.

This allows the LLM to load and understand the connections between related notes via backlinks.

Usage

Stdio Transport (default)

obsidian_fetch /path/to/your/vault

Streamable HTTP Transport

To run the server as an HTTP server:

obsidian_fetch /path/to/your/vault --transport streamable-http

By default, the server listens on http://localhost:9292. You can customize the port:

obsidian_fetch /path/to/your/vault --transport streamable-http --port 3000

Frequently Asked Questions

Is Obsidian_fetch safe to use?

Obsidian_fetch has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.

How do I install Obsidian_fetch?

Obsidian_fetch can be installed by cloning its GitHub repository and following the setup instructions in the README.

What can Obsidian_fetch do?

Obsidian_fetch provides 4 tools: Installation, Usage, Contributing, License. See the full tools list on the server page for descriptions and parameters.

What AI clients work with Obsidian_fetch?

Obsidian_fetch is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.

Is Obsidian_fetch actively maintained?

Obsidian_fetch is recently maintained — last commit was 43 days ago. It has 2 GitHub stars.

ObsidianFetch

Languages: 日本語

MCP servers focused on fetching and presenting information from Obsidian vaults.

The existing MCP server has the following drawbacks:

It supports many commands, which can cause slow prompt loading when computational resources are limited.
When reading a note labeled "Sample Note", it is necessary to search for its path first before loading it, but the LLM may not always follow this procedure.
Some tools include unnecessary options, leading the LLM to sometimes fail to invoke them correctly.

These issues become particularly noticeable when running an LLM on a local GPU.
To address this, we developed a new MCP server that simply retrieves and loads lists of notes.

The new server also provides the following additional features:

When the LLM attempts to retrieve link information by searching with brackets like [[link name]], the server automatically removes any characters that cannot be used in links.
In addition to loading the note contents, it also displays backlinks—notes that link to the currently opened note.
- This allows the LLM to load and understand the connections between related notes via backlinks.

Installation

gem install obsidian_fetch

Usage

Stdio Transport (default)

obsidian_fetch /path/to/your/vault

Streamable HTTP Transport

To run the server as an HTTP server:

obsidian_fetch /path/to/your/vault --transport streamable-http

By default, the server listens on http://localhost:9292. You can customize the port:

obsidian_fetch /path/to/your/vault --transport streamable-http --port 3000

Tools

read: Read a note from the Obsidian vault. If multiple notes with the same name are found, all will be shown.
list: Search for files with matching names partially.

Contributing

Bug reports and pull requests are welcome on GitHub at https://github.com/soukouki/obsidian_fetch.

License

The gem is available as open source under the terms of the MIT License.