memory-mcp CLAUDE.md

memory-mcp CLAUDE.md is an instructions file for coding agents from yuvalsuede/memory-mcp. It costs 866 tokens per session, scanned A, original, MIT.

Project instructions and memory notes for the memory-mcp system, including its design, decisions, pitfalls, and current progress. It uses CLAUDE.md and a separate state file to retain context across coding sessions.

In plain words
What is it for?
Use it when setting up, searching, consolidating, or checking the status of project memory, or when continuing work on a large project.
Why use it?
It helps an agent recover project context and find deeper information without relying on a small conversation window. It also records decisions and known setup problems in one place.

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/yuvalsuede/memory-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/yuvalsuede/memory-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 memory-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yuvalsuede/memory-mcp/claude-md.svg)](https://agentmods.dev/instructions/yuvalsuede/memory-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yuvalsuede/memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yuvalsuede/memory-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 866 This file is loaded in full into every session.
When invoked 866 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 $0.00866 $0.00866
Opus 5 $0.00433 $0.00433
Sonnet 5 $0.00173 $0.00173
Haiku 4.5 $0.00087 $0.00087

Measured 5d ago against content hash 52716eb90686, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-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 5d 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

memory-mcp

Last updated: 2026-01-27 | 28 active memories, 28 total

Architecture

  • Memory system needs two modes: instant session recovery and mid-session deep context recall for large projects [memory-design, context-management]
  • Two-tier memory system with CLAUDE.md (top 150 lines) and .memory/state.json (unlimited storage) for project contex... [memory, architecture]
  • Renamed npm package from memory-mcp to claude-memory-mcp [packaging, branding]
  • Official MCP registry publisher requires manual cloning and building from GitHub source repository, not a standard np... [deployment, mcp-registry]

Key Decisions

  • Project memory must be scalable beyond typical 2-5K token context window limits [scaling, context-management]
  • Created a CLI tool for memory-mcp with commands like setup, init, status, search, ask, consolidate, and key management [cli, tooling]
  • Memory extractor modified to handle new transcript format with nested message content and tool interactions within as... [memory-mcp, architecture]
  • Corrected Anthropic Claude model ID from claude-haiku-4-20250414 to claude-3-5-haiku-20241022 [llm, configuration]
  • Prepared documentation including README.md, ARCHITECTURE.md, LICENSE, CHANGELOG.md for project release [documentation, release-prep]
  • Renamed npm package from claude-memory-mcp to claude-code-memory after verifying availability and selecting the m... [npm, packaging]
  • Resolved MCP SDK compatibility by switching back to zod v4 after initially attempting zod v3 [dependency, typescript]
  • Proposed version bump to 1.0.1 to distribute clean build with zod v4 to npm users [versioning, npm]
  • Bumped package version to 1.0.2 to support MCP registry validation requirements [versioning, deployment]
  • Identified two separate publish workflows: one for Smithery using npx @smithery/cli deploy and another for official... [deployment, registry]

Gotchas & Pitfalls

  • Transcript parsing originally failed due to mismatched entry types: expected 'human/user' but actual format uses 'use... [memory-mcp, parsing]
  • MCP server communication fails due to zod version incompatibility between zod v3 and v4, causing JSON parsing errors ... [dependency, typescript]
  • Zod v3 causes infinite type recursion with MCP SDK's server.tool(), requiring a downgrade to zod v4 [typescript, dependency, sdk]
  • Smithery CLI deploy fails for stdio-based local servers, which cannot be published through their current web UI desig... [deployment, registry]

Read the full file on GitHub · 44 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. 5d ago First seen · 44 lines · 866 tokens per session scan A 52716eb90686

Subscribe to this mod's changes

memory-mcp CLAUDE.md is an instructions file published in the GitHub repository yuvalsuede/memory-mcp (98 stars, last pushed 7mo ago), licensed MIT. It adds 866 tokens to every session, about $0.0043 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.