knowledge-base-mcp CLAUDE.md

knowledge-base-mcp CLAUDE.md is an instructions file for coding agents from Leon4s4/knowledge-base-mcp. It costs 559 tokens per session, scanned A, original, MIT.

A project instruction file for a Python knowledge-base server that gives GitHub Copilot persistent memory using a local database.

In plain words
What is it for?
Use it when installing dependencies, running the server, checking its tests, loading initial knowledge, or understanding its main files and tools.
Why use it?
It tells the coding agent how the project is organised, which commands test it, and how to start it, reducing guesswork when making changes.

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/leon4s4/knowledge-base-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/Leon4s4/knowledge-base-mcp

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 knowledge-base-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/leon4s4/knowledge-base-mcp/claude-md.svg)](https://agentmods.dev/instructions/leon4s4/knowledge-base-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/leon4s4/knowledge-base-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/leon4s4/knowledge-base-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 559 This file is loaded in full into every session.
When invoked 559 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 $0.00559 $0.00559
Opus 5 $0.00280 $0.00280
Sonnet 5 $0.00112 $0.00112
Haiku 4.5 $0.00056 $0.00056

Measured 4d ago against content hash 2f622b9b6f99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-base-mcp 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 4d 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 · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 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 (claude.ai/code) when working with code in this repository.

Project Overview

This is a Knowledge Base MCP (Model Context Protocol) Server - a mem0-like memory system for GitHub Copilot that provides persistent knowledge storage and retrieval using local ChromaDB. The server enables GitHub Copilot to save and retrieve contextual information about development environments.

Key Commands

Testing and Development

# Install dependencies
pip install -r requirements.txt

# Test server functionality
python test_server.py

# Test initial knowledge loading
python test_initial_knowledge.py

# Run usage examples
python examples.py

# Start the MCP server
python kb_server.py

No Build/Lint Commands

This is a pure Python project with no formal build, lint, or test runner configuration. Tests are run directly as Python scripts.

Architecture

Core Components

  • kb_server.py: Main FastMCP server with ChromaDB integration
  • ChromaDB: Local vector database for semantic search using all-MiniLM-L6-v2 embeddings
  • FastMCP: MCP server framework for tool definitions

Key Tools

  • kb_save: Save memories with automatic metadata extraction
  • kb_search: Semantic search with vector similarity
  • kb_list: List all saved memories with filtering
  • kb_delete: Remove memories by ID

Memory Types

  • Environment: URLs, configurations, dashboard locations
  • Code Snippet: Code examples and patterns
  • Operational: Troubleshooting steps and fixes
  • Architectural: Design decisions and system patterns

Data Flow

  1. Content saved via kb_save → metadata extraction → ChromaDB storage
  2. Search queries → vector embedding → similarity search → ranked results
  3. All data stored locally in kb_data/ directory

Configuration

Environment Variables

  • KB_DATA_DIR: ChromaDB storage directory (default: ./kb_data)
  • KB_INITIAL_FILE: Optional initial knowledge file to bootstrap database

Read the full file on GitHub · 72 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. 4d ago First seen · 72 lines · 559 tokens per session scan A 2f622b9b6f99

Subscribe to this mod's changes

knowledge-base-mcp CLAUDE.md is an instructions file published in the GitHub repository Leon4s4/knowledge-base-mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 559 tokens to every session, about $0.0028 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.