mcp-vault CLAUDE.md

mcp-vault CLAUDE.md is an instructions file for coding agents from phate45/mcp-vault. It costs 503 tokens per session, scanned A, original, MIT.

Development instructions for an MCP server that manages an Obsidian vault, a collection of Markdown notes. It communicates with Obsidian through a local REST API and reads Markdown files from the filesystem.

In plain words
What is it for?
Use them to understand the codebase, add and register tools, and implement handlers for reading or changing vault content.
Why use it?
They explain the project structure and the required pattern for adding new tools, reducing uncertainty when maintaining the server.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/phate45/mcp-vault/claude-md
Clone the repo
git clone --depth 1 https://github.com/phate45/mcp-vault

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-vault CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/phate45/mcp-vault/claude-md.svg)](https://agentmods.dev/instructions/phate45/mcp-vault/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/phate45/mcp-vault/claude-md"><img src="https://agentmods.dev/badge/instructions/phate45/mcp-vault/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 503 This file is loaded in full into every session.
When invoked 503 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00503 $0.00503
Opus 5 $0.00251 $0.00251
Sonnet 5 $0.00101 $0.00101
Haiku 4.5 $0.00050 $0.00050

Measured 5d ago against content hash 7f36c3754f04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-vault CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with code in this repository.

Project Overview

MCP server for Obsidian vault operations. Communicates with Obsidian via the Local REST API plugin (custom fork required for move operations) and reads markdown files directly from the filesystem.

Project Structure

  • src/mcp_vault/__init__.py - Package entry point
  • src/mcp_vault/server.py - MCP server with tool registration and handlers
  • src/mcp_vault/tools.py - Tool definitions using ToolHandler base class
  • src/mcp_vault/implementation.py - Markdown parsing and heading analysis logic

Contributing Guidelines

Adding a New Tool

  1. Create a new class in tools.py that extends ToolHandler
  2. Implement get_tool_description() to return MCP Tool object with JSON schema
  3. Implement run_tool(args: dict) with the tool's logic
  4. Register the tool in register_tools() function by adding it to the returned dictionary

Example pattern:

class MyNewTool(ToolHandler):
    def get_tool_description(self) -> Tool:
        return Tool(name="my_tool", ...)

    async def run_tool(self, args: dict) -> list[TextContent]:
        # Implementation here
        pass

Code Conventions

  • All server operations use async/await
  • Tools return list[TextContent] from MCP types
  • File paths in arguments are relative to vault root
  • Use the ToolHandler pattern for consistency

Runtime Requirements

  • Python >=3.13: Required for modern type hints and async features
  • Environment Variable: VAULT_PATH must be set to absolute path of Obsidian vault
  • External Dependencies:
    • Obsidian Local REST API plugin (custom fork) running on localhost:27124
    • API token read from .obsidian/plugins/obsidian-local-rest-api/data.json
    • See README for details on the required fork for move_file functionality

Testing

TODO: No tests currently exist. Once test files are added or the testing TODO in README is addressed, update this section with:

  • Testing approach and framework
  • How to run tests
  • Any special considerations for testing MCP tools

Read the full file on GitHub · 60 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 60 lines · 503 tokens per session scan A 7f36c3754f04

Subscribe to this mod's changes

mcp-vault CLAUDE.md is an instructions file published in the GitHub repository phate45/mcp-vault (1 stars, last pushed 9mo ago), licensed MIT. It adds 503 tokens to every session, about $0.0025 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.