What is mcp-neo4j-agent-memory CLAUDE.md?

A project instruction file for an AI coding assistant working on a server that connects Claude Desktop to Neo4j, a database designed for linked data. It documents the project structure, design choices, and development commands.

Use it when developing or maintaining this Neo4j memory server, including its data model, validation, database sessions, and command-line workflow.

It gives the assistant the project context needed to make changes that fit the existing code and avoid breaking important conventions.

How knowall-ai/mcp-neo4j-agent-memory configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to knowall-ai/mcp-neo4j-agent-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/knowall-ai/mcp-neo4j-agent-memory/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/knowall-ai/mcp-neo4j-agent-memory

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/knowall-ai/mcp-neo4j-agent-memory/claude-md/github.svg)](https://agentmods.dev/instructions/knowall-ai/mcp-neo4j-agent-memory/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/knowall-ai/mcp-neo4j-agent-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/knowall-ai/mcp-neo4j-agent-memory/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/knowall-ai/mcp-neo4j-agent-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/knowall-ai/mcp-neo4j-agent-memory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 930 This file is loaded in full into every session.

When invoked 930 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00930	$0.00930
Opus 5	$0.00465	$0.00465
Sonnet 5	$0.00186	$0.00186
Haiku 4.5	$0.00093	$0.00093

Measured 10d ago against content hash 9799b6918cd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-neo4j-agent-memory 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 10d 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 · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 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 an MCP (Model Context Protocol) server that bridges Neo4j graph database with Claude Desktop. It provides both basic Neo4j operations and specialized memory-focused tools optimized for AI agents and conversational AI.

Key Architecture

The codebase follows a three-layer architecture:

Entry Layer (src/index.ts): Handles environment configuration and server lifecycle
Server Layer (src/server.ts): Implements MCP protocol with 10 specialized tools
Client Layer (src/neo4j-client.ts): Abstracts Neo4j driver operations

Critical Design Decisions

Entity-Based Memory System: The remember/recall/connect_memories tools promote storing separate nodes for each entity rather than complex properties
Type Guards: Every tool has a corresponding isXArgs() function for runtime validation
Session Management: Neo4j sessions are created per query and properly closed to prevent connection leaks
Integer Conversion: Neo4j's Integer type is automatically converted to JavaScript numbers

Development Commands

# Build TypeScript to JavaScript
npm run build

# Watch mode for development
npm run watch

# Run MCP inspector for debugging
npm run inspector

# Run all tests (from project root)
node tests/run-all-tests.js

# Run a single test
node tests/test-remember.js

Testing Strategy

Tests spawn the MCP server as a subprocess and communicate via JSON-RPC:

Each test creates its own test data
Tests use the mcp-test database for isolation
Delete tests clean up after themselves
Environment variables are loaded from .env file

Environment Configuration

Required environment variables (store in .env):

NEO4J_PASSWORD=your_password
NEO4J_DATABASE=neo4j  # or specific database for Enterprise
NEO4J_URI=bolt://localhost:7687
NEO4J_USERNAME=neo4j

Tool Implementation Pattern

Read the full file on GitHub · 124 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.

10d ago First seen · 124 lines · 930 tokens per session scan A 9799b6918cd8

Subscribe to this mod's changes

mcp-neo4j-agent-memory CLAUDE.md is an instructions file published in the GitHub repository knowall-ai/mcp-neo4j-agent-memory (69 stars, last pushed 10mo ago), licensed MIT. It adds 930 tokens to every session, about $0.0047 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 2026-08-30.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-neo4j-agent-memory: Instructions file for Claude Code