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.
npx agentmods add instructions/foxj77/mcp-memory-server/claude-mdgit clone --depth 1 https://github.com/foxj77/mcp-memory-serverWrote 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.
[](https://agentmods.dev/instructions/foxj77/mcp-memory-server/claude-md)<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>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 | $0.01493 | $0.01493 |
| Opus 5 | $0.00746 | $0.00746 |
| Sonnet 5 | $0.00299 | $0.00299 |
| Haiku 4.5 | $0.00149 | $0.00149 |
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. 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.
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.
- 4d ago First seen · 94 lines · 1,493 tokens per session scan A 76fe03752c98
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.
Other instructions, from other repositories
agents-remember AGENTS.md
Instructions for Foxfire1st/agents-remember, covering agents remember source checkout instructions, start here — route by role, memory and onboarding, memory retrieval strategies and source layout.
Perenna AGENTS.md
Instructions for scarletkc/Perenna, covering perenna agent guidelines, start with the project contract, environment, implementation boundaries and generated and versioned artifacts.
nobrainr CLAUDE.md
Claude Code instructions for vicquick/nobrainr, covering nobrainr — collective agent memory service, what this is, canonical categories, architecture and routing (when using a reverse proxy).
Muninn GEMINI.md
Gemini CLI instructions for wjohns989/Muninn, covering muninn mcp — sota+ development context, 🚀 sota+ development philosophy, 🛠 operational guidelines (always-on), 🏗 system architecture and 📂 project structure.
flux-memory CLAUDE.md
Instructions for harsh5i/flux-memory, covering flux memory v0.5 — claude.md, hard constraints (never deviate), repo layout, development rules and status.
locus AGENTS.md
Instructions for Magnifico4625/locus, covering agents, mission, core working style, collaboration contract and product rules.