simple-memory-mcp copilot-instructions.md

Instructions for a TypeScript memory server that stores information in a SQLite database and supports full-text search, meaning it can find words inside saved content.

In plain words
What is it for?
Installing dependencies, building and testing the server, and storing, searching, updating, deleting, or counting saved memories through commands or tools.
Why use it?
They provide a reference for building, testing, and using persistent memory instead of losing useful information between tasks or sessions.

Instructions file for GitHub Copilot

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/chrisribe/simple-memory-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/chrisribe/simple-memory-mcp

Made for: GitHub Copilot.

Per session 450 This file is loaded in full into every session.
When invoked 450 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 $0.00450 $0.00450
Opus 5 $0.00225 $0.00225
Sonnet 5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 2d ago against content hash 9fe51af73ca2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simple-memory-mcp copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 58 lines

What it actually says

Simple Memory MCP Server

TypeScript MCP server for persistent memory storage with SQLite FTS5. Works as both MCP server and CLI tool.

Quick Reference

Build & Test (All operations < 10 seconds)

npm install          # Install dependencies
npm run build        # Build TypeScript → JavaScript
npm test             # Run all tests

CLI Commands

# Store
node dist/index.js store --content "text" --tags "tag1,tag2"

# Search
node dist/index.js search --query "text"          # By content
node dist/index.js search --tags "tag1"           # By tags

# Update
node dist/index.js update --hash "abc..." --content "new text" --tags "new,tags"

# Delete
node dist/index.js delete --tag "tagname"         # By tag
node dist/index.js delete --hash "abc..."         # By hash

# Stats
node dist/index.js stats

Database

  • Default: ./memory.db
  • Custom: Set MEMORY_DB=/path/to/db environment variable
  • Format: SQLite with FTS5 full-text search, WAL mode

Project Structure

src/
├── services/memory-service.ts  # Core SQLite + FTS5 operations
├── tools/                      # MCP tools: store, search, update, delete, stats
├── tests/                      # Comprehensive test suite
└── utils/                      # JSON/CLI parsing, debug

Architecture

  • ES Modules: Use .js extensions in imports
  • TypeScript: Target ES2022, outputs to dist/
  • Database: better-sqlite3 with FTS5, prepared statements
  • MCP: @modelcontextprotocol/sdk
  • Performance: Sub-millisecond operations, 2,000-10,000 ops/sec

Troubleshooting

  • Module errors: Run npm install
  • Build errors: Run npm run build
  • Database errors: Check MEMORY_DB path is writable
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. 2d ago First seen · 58 lines · 450 tokens per session scan A 9fe51af73ca2

Subscribe to this mod's changes

simple-memory-mcp copilot-instructions.md is an instructions file published in the GitHub repository chrisribe/simple-memory-mcp (8 stars, last pushed 4mo ago), licensed MIT. It adds 450 tokens to every session, about $0.0022 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.