mcp-brain: Instructions file for Claude Code

CLAUDE.md

mcp-brain CLAUDE.md is an instructions file for Claude Code from PierfrancescoLijoi/mcp-brain. It costs 837 tokens per session, scanned A, original, MIT.

Project instructions for `mcp-brain`, a local memory server that stores code-project context, design decisions, and session snapshots in a SQLite database. It explains the project’s commands, architecture, and three levels of stored memory.

In plain words
What is it for?
Use it when installing, running, or changing the server, or when working with its memory scoring and context-loading behavior.
Why use it?
It gives an agent the project-specific rules needed to work on `mcp-brain` without rebuilding its context from scratch.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is PierfrancescoLijoi/mcp-brain's own configuration. It tells Claude Code how to work on mcp-brain 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-brain configures →

Reuse

Borrowing it

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

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-brain CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pierfrancescolijoi/mcp-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/pierfrancescolijoi/mcp-brain/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 837 This file is loaded in full into every session.
When invoked 837 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 $0.00837 $0.00837
Opus 5 $0.00418 $0.00418
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00084 $0.00084

Measured 9d ago against content hash c244c1fe1b0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-brain 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 9d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 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.

What this project is

mcp-brain is a persistent memory MCP server for Claude Code. It stores project context, architectural decisions, and session snapshots in a local SQLite database (~/.mcp-brain/brain.db), then serves them back to Claude at the start of each session — eliminating context rebuilding overhead.

Commands

Install in editable mode:

pip install -e .

Run the server directly (dev):

python run.py

Run via installed entry point:

mcp-brain

There is no test suite or linter configured yet.

Architecture

Data model — three memory levels

Every memory has a computed score (0.0–1.0) that determines its level:

Level Score threshold When loaded
L1 ≥ 0.7 Every session (brain_get_context) — ~70 tokens
L2 ≥ 0.4 On-demand (brain_get_decisions) — ~200–400 tokens
L3 < 0.4 Archive only, never served

Scoring weights (src/brain/scorer.py): recency 35%, frequency 30%, file impact 20%, explicit flag 15%. Recency decays linearly to 0 over 30 days.

Request flow

Claude calls MCP tool
  → src/tools/mcp_tools.py  (FastMCP tool definitions)
  → src/brain/retriever.py  (business logic: scoring, level assignment)
  → src/brain/compressor.py (builds YAML context strings)
  → src/storage/db.py       (SQLite reads/writes to ~/.mcp-brain/brain.db)

MCP tools (exposed to Claude)

Tool Purpose
brain_init Register a project (call once per repo)
brain_get_context Load L1 context — call at session start
brain_get_decisions Load L2 decisions — call when historical context needed
brain_remember Store a memory; level auto-assigned by scorer
brain_save_session Save end-of-session snapshot (branch, wip, next steps)

Memory categories: decision, avoid, pattern, failed.

Read the full file on GitHub · 91 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. 9d ago First seen · 91 lines · 837 tokens per session scan A c244c1fe1b0e

Subscribe to this mod's changes

mcp-brain CLAUDE.md is an instructions file published in the GitHub repository PierfrancescoLijoi/mcp-brain (6 stars, last pushed 4mo ago), licensed MIT. It adds 837 tokens to every session, about $0.0042 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.

Related

Other instructions, from other repositories

repobrain copilot-instructions.md

Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.

study8677/repobrain · 229 tokens

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens