What is mcp-engram CLAUDE.md?

A project instruction file for MCP Engram, a Model Context Protocol server that stores a neuroscience-inspired knowledge graph in a local SQLite file. It documents the repository structure and development commands.

Use it when working on MCP Engram, its shared graph-memory library, or its server within the Nx monorepo.

It gives coding agents the project context needed to install dependencies, build the Nx monorepo, run tests, lint code, and start the server.

How shuruheel/mcp-engram configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shuruheel/mcp-engram. 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/shuruheel/mcp-engram/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/shuruheel/mcp-engram

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/shuruheel/mcp-engram/claude-md/github.svg)](https://agentmods.dev/instructions/shuruheel/mcp-engram/claude-md)

Your own site

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

Per session 998 This file is loaded in full into every session.

When invoked 998 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	$0.00998	$0.00998
Opus 5.5	$0.00399	$0.00399
Sonnet 5.5	$0.00200	$0.00200
Haiku 4.5	$0.00100	$0.00100

Measured 2mo ago against content hash 2af75823aa17, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-engram 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 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

MCP Engram — a Model Context Protocol server for building and exploring a cognitive neuroscience-inspired knowledge graph backed by SQLite. Models thought, emotion, reasoning, and episodic memory. Zero infrastructure — single file on disk, works offline.

Build & Development Commands

# Install dependencies
npm install

# Build all projects
npx nx run-many -t build

# Build individual projects
npx nx build mcp-engram              # MCP server (ESM, output: dist/servers/mcp-engram)
npx nx build graphrag-memory         # Shared types library (CJS, output: dist/libs/graphrag-memory)

# Serve server in dev mode
npx nx serve mcp-engram

# Test
npx nx test graphrag-memory          # Library tests
npx nx test mcp-engram               # Server tests
npx nx test mcp-engram -- --testPathPatterns=sqlite   # Run single test file by pattern (Jest 30: flag is plural)

# Lint
npx nx lint mcp-engram
npx nx lint graphrag-memory

# Run across all projects
npx nx run-many -t test
npx nx run-many -t lint

Architecture

Nx Monorepo

servers/mcp-engram — Main MCP server (TypeScript application)

Entry: src/main.ts → src/main/index.ts (server init, SQLite setup, MCP wiring)
src/main/tools.ts — MCP tool definitions and request handlers (8 tools)
src/main/prompts.ts — System prompts and tool-specific prompts
src/storage/sqlite.ts — SqliteBackend class: implements StorageBackend interface
src/storage/schema.ts — SQLite DDL (nodes, edges, aliases, observations, FTS5)
src/storage/fts.ts — FTS5 query builder
src/storage/validation.ts — Provenance and confidence validation
src/types/ — All TypeScript interfaces, enums, StorageBackend interface
Transport: StdioServerTransport (stdin/stdout)

libs/graphrag-memory — Shared type definitions library

Exports: Entity, Relation, KnowledgeGraph, KnowledgeGraphMemory, Source, EmotionalEvent
Path alias: @mcp-engram/graphrag-memory

Read the full file on GitHub · 92 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.

2mo ago First seen · 92 lines · 998 tokens per session scan A 2af75823aa17

Subscribe to this mod's changes

mcp-engram CLAUDE.md is an instructions file published in the GitHub repository shuruheel/mcp-engram (24 stars, last pushed 3mo ago), licensed MIT. It adds 998 tokens to every session, about $0.0040 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 2026-08-30.

Databases Memory and context

mcp-engram CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-engram CLAUDE.mdshuruheel/mcp-engram	Instructions file	24	3mo ago	MIT	A	998	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-engram: Instructions file for Claude Code