mcpField
K
Knowledge_vault

Knowledge_vault

Local
github.com/fak111Memory & Knowledge6Updated 74w ago
Repository

About Knowledge_vault

Knowledge_vault is a local knowledge-management MCP server built with FastMCP, for people who want to save and retrieve records in their home directory. It supports automatic titles and tags, fuzzy search, and usage statistics, with thread-safe storage.

Key features

  1. 01Automatically generate knowledge titles and tags
  2. 02Search fuzzily and filter by tags
  3. 03Suggest tags from content
  4. 04View knowledge-base usage statistics
  5. 05Store data thread-safely in the home directory

Use cases

  1. 01Save programming tips and personal notes
  2. 02Find stored records by keyword
  3. 03Organize and filter knowledge with tags
  4. 04Review knowledge-base record statistics

MCP support

The MCP server provides tools to store and search records, list recent entries, retrieve entries by ID, suggest tags, search by tags, and view statistics.

#knowledge-vault#knowledge-management#mcp-server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README
Project Logo

Local Store MCP

Your Data, Store Local

Demo Video

https://github.com/user-attachments/assets/4b8f11cd-bb9f-4822-b241-60ecd60bf39f

Features

  • ✅ Smart Storage: Auto-generate titles and tags
  • 🔍 Powerful Search: Support fuzzy search and tag filtering
  • 🏷️ Smart Tags: AI-suggested tags based on content
  • 📊 Statistics: Knowledge base usage statistics
  • 💾 Secure Storage: Data stored in user home directory
  • 🔒 Thread Safe: Support concurrent access

Project Structure

knowledge_vault/
├── __init__.py          # Package initialization
├── server.py            # FastMCP server main file
├── storage.py           # Knowledge storage module
└── search.py            # Search functionality module
pyproject.toml           # Project configuration
start_server_new.py      # Startup script

Installation

Install dependencies with uv
# Install uv if not already installed
curl -LsSf https://astral.sh/uv/install.sh | sh

# Sync dependencies
uv sync
Configure Claude Desktop

Edit ~/.config/claude_desktop_config.json:

{
  "mcpServers": {
    "knowledge-vault": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/your/local_store_mcp",
        "run",
        "python",
        "start_server_new.py"
      ],
      "cwd": "/path/to/your/local_store_mcp",
      "description": "Local Knowledge Management MCP Server"
    }
  }
}
Restart Claude Desktop

Restart Claude Desktop after configuration.

Usage

Store Knowledge
Store a programming tip: Using Python list comprehension makes code more concise
Search Knowledge
Search for Python knowledge
View Statistics
Show knowledge base statistics

Available Tools

  1. store_knowledge - Store knowledge records
  2. search_knowledge - Search knowledge records
  3. list_recent - View recent records
  4. get_knowledge - Get record by ID
  5. suggest_tags - Suggest tags
  6. search_by_tags - Search by tags
  7. get_stats - Get statistics

Data Storage

  • Location: ~/.knowledge-vault/knowledge.jsonl
  • Format: JSON Lines
  • Thread Safe: File locking for concurrent access

Tech Stack

  • FastMCP: MCP server framework
  • Pydantic: Data validation
  • uv: Modern Python package management
  • Python 3.10+: Runtime environment

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.