agentmods.dev

mcp-memory: Instructions file for Claude Code

CLAUDE.md

mcp-memory CLAUDE.md is an instructions file for Claude Code from oneKn8/mcp-memory. It costs 349 tokens per session, scanned A, original, MIT.

Project instructions for mcp-memory, a Python server that lets an agent save information and find it later by meaning. It stores memories locally, with separate collections for each project scope.

In plain words
What is it for?
Use it when developing mcp-memory: install its development dependencies, run tests, lint and format the code, check types, start the server, or understand its remember, recall, forget, and listing tools.
Why use it?
It gives contributors the commands, file layout, and design details needed to build, test, check, and run the project consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is oneKn8/mcp-memory's own configuration. It tells Claude Code how to work on mcp-memory itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-memory configures →

not rated 1repo 26d ago A scan 349 tokens original MIT
View source ↗ oneKn8/mcp-memory
Reuse

Borrowing it

Nothing to install: this file belongs to oneKn8/mcp-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/oneKn8/mcp-memory/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/oneKn8/mcp-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.

agentmods badge for mcp-memory CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/onekn8/mcp-memory/claude-md/github.svg)](https://agentmods.dev/instructions/onekn8/mcp-memory/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/onekn8/mcp-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/onekn8/mcp-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.

agentmods 80×15 button for mcp-memory CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/onekn8/mcp-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/onekn8/mcp-memory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 349 This file is loaded in full into every session.
When invoked 349 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00349 $0.00349
Opus 5.5 $0.00140 $0.00140
Sonnet 5.5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured 2mo ago against content hash 453509efc775, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-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 2mo 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 · 46 lines

What it actually says

mcp-memory

MCP server for persistent agent memory with semantic search.

Language

Python (3.11+)

Build & Run Commands

  • Install: pip install -e ".[dev]"
  • Test: pytest
  • Lint: ruff check .
  • Format: ruff format .
  • Type check: mypy mcp_memory
  • Run: python -m mcp_memory.server

Project Structure

  • mcp_memory/server.py - FastMCP server with tool definitions
  • mcp_memory/storage.py - ChromaDB wrapper (MemoryStore class)
  • mcp_memory/config.py - Environment variable configuration
  • mcp_memory/models.py - Data models (Memory, RecallResult)
  • tests/ - pytest tests

Architecture

  • FastMCP 3.0 for MCP protocol (stdio transport)
  • ChromaDB PersistentClient for vector storage (cosine similarity)
  • One ChromaDB collection per project scope
  • Default embedding model: all-MiniLM-L6-v2 (via sentence-transformers, auto-downloaded)
  • Data stored at ~/.mcp-memory/ (configurable via MCP_MEMORY_DATA_DIR)

MCP Tools

  • remember - Store a memory with content, tags, project, importance
  • recall - Semantic search across stored memories
  • forget - Delete memories by ID, project, or tags
  • list_memories - Browse memories with pagination and stats

Conventions

  • All tools return formatted strings
  • Tags stored as comma-separated strings in ChromaDB metadata
  • Per-project isolation via separate ChromaDB collections
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. 2mo ago First seen · 46 lines · 349 tokens per session scan A 453509efc775

Subscribe to this mod's changes

mcp-memory CLAUDE.md is an instructions file published in the GitHub repository oneKn8/mcp-memory (1 stars, last pushed 26d ago), licensed MIT. It adds 349 tokens to every session, about $0.0014 per session on Opus 5.5. 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.

Building agentsMemory and context
Related

mcp-memory CLAUDE.md compared with instructions from other repositories

mcp-memory CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-memory CLAUDE.mdoneKn8/mcp-memoryInstructions file126d agoMITA349Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode