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.
npx agentmods add instructions/alphaplapplap/mcp-memory-service/claude-mdgit clone --depth 1 https://github.com/alphaplapplap/mcp-memory-serviceWrote 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.
[](https://agentmods.dev/instructions/alphaplapplap/mcp-memory-service/claude-md)<a href="https://agentmods.dev/instructions/alphaplapplap/mcp-memory-service/claude-md"><img src="https://agentmods.dev/badge/instructions/alphaplapplap/mcp-memory-service/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03372 | $0.03372 |
| Opus 5 | $0.01686 | $0.01686 |
| Sonnet 5 | $0.00674 | $0.00674 |
| Haiku 4.5 | $0.00337 | $0.00337 |
Grade B, and why
mcp-memory-service CLAUDE.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# Setup: Configure mid-conversation hook in ~/.claude/settings.json How it starts
The opening of the file, as written. The whole thing — 322 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 this MCP Memory Service repository.
Note: Comprehensive project context has been stored in memory with tags
claude-code-reference. Use memory retrieval to access detailed information during development.
Overview
MCP Memory Service is a Model Context Protocol server providing semantic memory and persistent storage for Claude Desktop using ChromaDB and sentence transformers.
🧠 v7.1.0: Now features Natural Memory Triggers with intelligent automatic memory retrieval, 85%+ trigger accuracy, and multi-tier performance optimization!
🚀 v7.0.0: Features OAuth 2.1 Dynamic Client Registration and Dual Protocol Memory Hooks for Claude Code with automatic HTTP/MCP protocol detection.
Essential Commands
# Setup & Development
python scripts/installation/install.py # Platform-aware installation with backend selection
python scripts/installation/install.py --storage-backend hybrid # Hybrid setup (RECOMMENDED)
python scripts/installation/install.py --storage-backend cloudflare # Direct Cloudflare setup
uv run memory server # Start server (v6.3.0+ consolidated CLI)
pytest tests/ # Run tests
python scripts/validation/verify_environment.py # Check environment
python scripts/validation/validate_configuration_complete.py # Comprehensive configuration validation
# Memory Operations (requires: python scripts/utils/claude_commands_utils.py)
claude /memory-store "content" # Store information
claude /memory-recall "query" # Retrieve information
claude /memory-health # Check service status
# Configuration Validation
python scripts/validation/diagnose_backend_config.py # Validate Cloudflare configuration
# Backend Synchronization
python scripts/sync/sync_memory_backends.py --status # Check sync status
python scripts/sync/sync_memory_backends.py --dry-run # Preview sync
python scripts/sync/claude_sync_commands.py backup # Cloudflare → SQLite
python scripts/sync/claude_sync_commands.py restore # SQLite → Cloudflare
# Service Management
scripts/service/memory_service_manager.sh status # Check service status
scripts/service/memory_service_manager.sh start-cloudflare # Start with Cloudflare
# Natural Memory Triggers v7.1.0 (Latest)
node ~/.claude/hooks/memory-mode-controller.js status # Check trigger system status
node ~/.claude/hooks/memory-mode-controller.js profile balanced # Switch performance profile
node ~/.claude/hooks/memory-mode-controller.js sensitivity 0.7 # Adjust trigger sensitivity
node ~/.claude/hooks/test-natural-triggers.js # Test trigger system
# Debug & Troubleshooting
npx @modelcontextprotocol/inspector uv run memory server # MCP Inspector
python scripts/database/simple_timestamp_check.py # Database health check
df -h / # Check disk space (critical for Litestream)
journalctl -u mcp-memory-service -f # Monitor service logs
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.
- 4d ago First seen · 322 lines · 3,372 tokens per session scan B 4e6e52318ef6
mcp-memory-service CLAUDE.md is an instructions file published in the GitHub repository alphaplapplap/mcp-memory-service (9 stars, last pushed 11mo ago), licensed Apache-2.0. It adds 3,372 tokens to every session, about $0.0169 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.