Knowledge_vault
@fak111
About Knowledge_vault
A local knowledge management MCP server built with FastMCP framework.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"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"
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Knowledge_vault?
Knowledge_vault is a local knowledge management MCP server built with the FastMCP framework and Python. It enables users to store, search, and manage knowledge records directly on their machine, with features like automatic title generation, tag suggestion, and fuzzy search. It is intended for developers and power users who want a private, file-based knowledge base integrated with MCP-compatible clients (e.g., Claude Desktop).
How to use Knowledge_vault?
After installing dependencies with uv, add the server configuration to your Claude Desktop config file (~/.config/claude_desktop_config.json) using the provided JSON snippet, then restart Claude Desktop. Use natural language commands like “Store a programming tip: …” or “Search for Python knowledge” to interact with the server.
Key features of Knowledge_vault
- Smart storage with auto-generated titles and tags
- Fuzzy search and tag filtering
- AI-suggested tags based on content
- Knowledge base usage statistics
- Data stored securely in user home directory
- Thread-safe concurrent access with file locking
Use cases of Knowledge_vault
- Save programming tips and retrieve them later via search
- Organize notes by auto-suggested tags for quick filtering
- View statistics on how many records have been stored
- Retrieve a specific knowledge record by its ID
- Search across the knowledge base using fuzzy matching
FAQ from Knowledge_vault
Where does Knowledge_vault store data?
Data is stored in the user’s home directory at ~/.knowledge-vault/knowledge.jsonl in JSON Lines format.
How do I install Knowledge_vault for use with Claude Desktop?
Use uv to sync dependencies, then add the server configuration to ~/.config/claude_desktop_config.json as shown in the README, and restart Claude Desktop.
What tools does Knowledge_vault expose?
It provides seven tools: store_knowledge, search_knowledge, list_recent, get_knowledge, suggest_tags, search_by_tags, and get_stats.
Is Knowledge_vault safe to use concurrently?
Yes, the server is thread safe and uses file locking for concurrent access.
What runtime does Knowledge_vault require?
Python 3.10 or newer, along with the uv package manager for dependency management.
More Memory & Knowledge MCP servers
mcp-local-rag
nkapila6"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨
Memory Bank MCP Server
alioshrA Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Docs MCP Server
araboldGrounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools
Solomd
zhitongblogA markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
Context7 MCP - Up-to-date Docs For Any Cursor Prompt
upstashContext7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Comments