mcp-memory-server CLAUDE.md

mcp-memory-server CLAUDE.md is an instructions file for coding agents from foxj77/mcp-memory-server. It costs 1,493 tokens per session, scanned A, original, MIT.

Repository instructions for mcp-memory-server, a small project that packages a memory service in a container and makes it available over HTTP for Kubernetes deployments. The service stores its knowledge graph in a mounted data file.

In plain words
What is it for?
Use it when changing the Dockerfile, Helm chart, example deployment files, documentation, or smoke tests for this project.
Why use it?
It gives a coding agent the repository's structure, build and test commands, and important deployment constraints without requiring the agent to discover them first.

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/foxj77/mcp-memory-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/foxj77/mcp-memory-server

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-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/foxj77/mcp-memory-server/claude-md.svg)](https://agentmods.dev/instructions/foxj77/mcp-memory-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/foxj77/mcp-memory-server/claude-md"><img src="https://agentmods.dev/badge/instructions/foxj77/mcp-memory-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,493 This file is loaded in full into every session.
When invoked 1,493 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01493 $0.01493
Opus 5 $0.00746 $0.00746
Sonnet 5 $0.00299 $0.00299
Haiku 4.5 $0.00149 $0.00149

Measured 4d ago against content hash 76fe03752c98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-memory-server CLAUDE.md scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Requires `curl` and `jq`. The test is idempotent — safe to re-run against a live graph as it uses `smoke-test/` prefixed entity names and cleans up after itself.
CLAUDE.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 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 repo is

A thin packaging project — no application source code. It builds a container image that wraps the upstream @modelcontextprotocol/server-memory (stdio) with supergateway to expose it as an MCP Streamable HTTP endpoint suitable for Kubernetes workloads. The knowledge graph is persisted to /data/memory.jsonl on a mounted volume.

The entire runtime is two npm install -g packages plus a single CMD line — there is no application build step or lint config. Changes are almost always to Dockerfile, chart/, examples/*.yaml, README.md, or tests/smoke-test.sh.

Chart layout

chart/
├── Chart.yaml              # metadata; version stamped by CI at publish time
├── values.yaml             # all tunable values with inline constraint docs
├── values.schema.json      # JSON Schema — Helm validates values against this on install
└── templates/
    ├── _helpers.tpl        # name/label/image helpers
    ├── deployment.yaml     # replicas hardcoded to 1 — see inline comment for why
    ├── pvc.yaml            # accessMode hardcoded to ReadWriteOnce — see inline comment
    ├── service.yaml
    └── NOTES.txt           # post-install endpoint instructions

Build / run / test

# Local build + run
docker build -t mcp-memory-server .
docker run -p 3000:3000 -v $(pwd)/data:/data mcp-memory-server

# Smoke test (exercises all 7 MCP tools, verifies responses, then cleans up)
./tests/smoke-test.sh

# Against a remote deployment
MCP_URL=http://mcp-memory-server.my-namespace.svc.cluster.local:3000/mcp ./tests/smoke-test.sh

Requires curl and jq. The test is idempotent — safe to re-run against a live graph as it uses smoke-test/ prefixed entity names and cleans up after itself.

Images are published to ghcr.io/foxj77/mcp-memory-server by .github/workflows/publish.yaml when a GitHub Release is created. Multi-arch (amd64 + arm64). Manual builds (no release) can be triggered via workflow_dispatch and receive edge + sha- tags only.

Read the full file on GitHub · 94 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. 4d ago First seen · 94 lines · 1,493 tokens per session scan A 76fe03752c98

Subscribe to this mod's changes

mcp-memory-server CLAUDE.md is an instructions file published in the GitHub repository foxj77/mcp-memory-server (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,493 tokens to every session, about $0.0075 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.