Knowledge Base MCP

v1.0.0Knowledge & Memorystable

Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline.

aiai-agentsknowledge-basellmmcp
Share:
168
Stars
0
Downloads
0
Weekly
0/5

What is Knowledge Base MCP?

Knowledge Base MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to make every ai agent you use smarter. persistent memory with sqlite fts5, mcp server, obsidian sync, and self-learning intelligence pipeline.

Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Make every AI agent you use smarter. Persistent memory with

Use Cases

Persistent memory with SQLite
Obsidian sync
Self-learning intelligence
willynikes2

Maintainer

LicenseMIT
Languagejavascript
Versionv1.0.0
UpdatedMay 17, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y knowledge-base

Manual Installation

npx -y knowledge-base

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Knowledge Base MCP

Knowledge Base MCP Server is a persistent memory system for AI agents that uses SQLite FTS5 full-text search with BM25 ranking and local semantic embeddings via HuggingFace's all-MiniLM-L6-v2 model to store and retrieve information across sessions without external API calls. It exposes 16 MCP tools covering search, read/write, ingestion, classification, synthesis, and session capture — and optionally syncs bidirectionally with an Obsidian vault for human-readable knowledge management. Developers who work with multiple AI agents (Claude, Codex, Gemini) use it as a shared intelligence layer that learns over time and delivers highly token-efficient context summaries.

Prerequisites

  • Node.js 18 or later
  • npm for installation and the kb CLI
  • Optional: Obsidian installed with a vault directory if you want bidirectional Obsidian sync
  • Optional: API keys for KB_API_KEY_CLAUDE, KB_API_KEY_OPENAI, or KB_API_KEY_GEMINI if using AI-powered classification
1

Clone and install the server

Clone the repository, install dependencies, and link the kb CLI globally so it is accessible from any directory.

git clone https://github.com/willynikes2/knowledge-base-server.git
cd knowledge-base-server
npm install
npm link
2

Run the interactive setup wizard

The setup wizard configures your password, port, optional Obsidian vault path, and which AI agents to register. Use --auto for a non-interactive setup.

# Interactive
kb setup

# Automated with flags
kb setup --auto --password=yourpass --vault=~/obsidian-vault --agents=claude,codex --deploy=systemd
3

Set required environment variables

At minimum, set KB_PASSWORD for authentication. Set KB_PORT if you want a non-default port (default 3838). Add Obsidian and AI API keys as needed.

export KB_PASSWORD=your-secure-password
export KB_PORT=3838
export OBSIDIAN_VAULT_PATH=~/obsidian-vault
export KB_API_KEY_CLAUDE=sk-ant-...
4

Register the server with Claude and other agents

Run `kb register` to automatically update the MCP configuration for all registered agents. This makes all 16 MCP tools available without manual JSON editing.

kb register
5

Ingest initial knowledge

Use kb_ingest to load existing documents, notes, or code into the knowledge base. The server indexes content with both keyword (FTS5) and semantic (embedding) search.

# Via CLI
kb ingest ~/documents/notes.md

# Or ask Claude after setup
# "Ingest the contents of ~/documents/notes.md into the knowledge base"

Knowledge Base MCP Examples

Client configuration

After running `kb register`, the configuration is written automatically. For manual setup, the server runs on a local port that the MCP client connects to.

{
  "mcpServers": {
    "knowledge-base": {
      "command": "npx",
      "args": ["-y", "knowledge-base"],
      "env": {
        "KB_PASSWORD": "your-secure-password",
        "KB_PORT": "3838",
        "OBSIDIAN_VAULT_PATH": "/path/to/your/obsidian-vault"
      }
    }
  }
}

Prompts to try

Use Claude to search, store, and reason over your persistent knowledge base across sessions.

- "Search the knowledge base for anything related to authentication patterns I've used before"
- "Give me a token-optimized briefing on the current project context"
- "Store a note: decided to use Supabase for auth because of built-in RLS support"
- "Synthesize everything in the knowledge base about our API design decisions"
- "Classify and promote the last session's notes to permanent knowledge"

Troubleshooting Knowledge Base MCP

kb command not found after npm link

Check that your npm global bin directory is on your PATH. Run `npm bin -g` to find the directory and add it to your shell profile (e.g., export PATH="$(npm bin -g):$PATH" in ~/.zshrc).

Semantic search returns irrelevant results

The local embedding model (all-MiniLM-L6-v2) must be downloaded on first run, which can take a few minutes. Wait for initialization to complete before ingesting content. Check server logs for download progress.

Obsidian vault changes are not reflected in the knowledge base

Ensure OBSIDIAN_VAULT_PATH is set to the exact vault root directory. The server watches for file changes automatically, but large vaults may take time to index. Run `kb sync` to trigger a manual sync.

Frequently Asked Questions about Knowledge Base MCP

What is Knowledge Base MCP?

Knowledge Base MCP is a Model Context Protocol (MCP) server that make every ai agent you use smarter. persistent memory with sqlite fts5, mcp server, obsidian sync, and self-learning intelligence pipeline. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Knowledge Base MCP?

Install via npm with the command: npx -y knowledge-base. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Knowledge Base MCP?

Knowledge Base MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Knowledge Base MCP free to use?

Yes, Knowledge Base MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "knowledge-base": { "command": "npx", "args": ["-y", "knowledge-base"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Knowledge Base MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides