mcp-memory-service is a self-hosted memory backend that lets AI agents store and retrieve shared project context through REST, MCP, OAuth, a command-line interface, and a dashboard. It is intended for agent pipelines and clients such as LangGraph, CrewAI, AutoGen, Claude Desktop, and OpenCode, with support for knowledge graphs and memory consolidation. The catalogue includes skills, agents, commands, instructions, hooks, a setting, an MCP entry, and a plugin for its workflows.
Borrowing it
Nothing to install: this file belongs to doobidoo/mcp-memory-service. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/doobidoo/mcp-memory-service/main/CLAUDE.mdgit clone --depth 1 https://github.com/doobidoo/mcp-memory-serviceWrote 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/doobidoo/mcp-memory-service/claude-md)<a href="https://agentmods.dev/instructions/doobidoo/mcp-memory-service/claude-md"><img src="https://agentmods.dev/badge/instructions/doobidoo/mcp-memory-service/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 5.1 | $0.07166 | $0.07166 |
| Opus 5 | $0.03583 | $0.03583 |
| Sonnet 5 | $0.01433 | $0.01433 |
| Haiku 4.5 | $0.00717 | $0.00717 |
Grade B, and why
mcp-memory-service CLAUDE.md scanned grade B 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
block in `~/.claude/settings.json` before assuming the skill is missing. How it starts
The opening of the file, as written. The whole thing — 448 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 this MCP Memory Service repository. It is written to be self-sufficient: a model should be able to work correctly here from this file alone, without filling gaps from prior knowledge.
Personal Customizations: You can create
CLAUDE.local.md(gitignored) for personal notes, custom workflows, or environment-specific instructions. This file contains shared project conventions.
Information Lookup: Files first, memory second, user last. See
.claude/directives/memory-first.mdfor strategy. Comprehensive project context is stored in the MCP Memory Server with tagclaude-code-reference.
Non-Negotiables (hard rules)
Quick reference; each rule is expanded in the sections below. Violations cause real incidents.
- Development happens on GitHub.
originisgithub.com:doobidoo/mcp-memory-service; CI is GitHub Actions (.github/workflows/); issues, PRs, releases and the tag push that starts a release all live there, andghis the CLI for all of it. GitLab is a push mirror that receives fast-forwards ofmainand never tags (see "Source Control & Hosting"). - Never manually bump versions. Follow the documented release workflow for every version bump and release.
- Run
bash scripts/pr/pre_pr_check.shbefore every PR. It is the mandatory pre-PR gate and must pass. - Use the project venv. Run
.venv/bin/pythonand.venv/bin/pytest(Python 3.12) — the system interpreters are not the project environment. - Store context in the MCP Memory Server first, tagged
mcp-memory-service. Claude Code's file-based memory (~/.claude/projects/<project>/memory/) may run alongside it as a local cache — it is a supplement, not a substitute, and it lives outside the repo. Never commit memory files into the working tree. - Access
Memoryfields by attribute (memory.tags), never viamemory.metadata.get('tags'). This has caused 3 production bugs. - Sanitize user-provided values in logs with
_sanitize_log_value()(frommcp_memory_service.compat). - MCP server configs go in
.mcp.json, notsettings.json. - Update
site/index.htmlversion strings on every MINOR/MAJOR release (a CI gate enforces this). - Never click "Always allow" on heredoc commands — it corrupts
.claude/settings.local.json. - Before any SSH/network task, verify
hostnameand connection direction (source → target). - Report outcomes faithfully. "Tests pass" means you ran them and saw them pass; if a step was skipped or failed, say so with the output.
- Write in the maintainer's or contributor's own voice. Commit messages, PR descriptions, CHANGELOG entries, issue/PR comments, and release notes read as authored by the maintainer or contributor.
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.
- today Changed · +39 lines · +785 tokens per session scan A → B df54f440dc18
- 8d ago First seen · 409 lines · 6,381 tokens per session scan A 4b40df7460eb
mcp-memory-service CLAUDE.md is an instructions file published in the GitHub repository doobidoo/mcp-memory-service (1,929 stars, last pushed today), licensed Apache-2.0. It adds 7,166 tokens to every session, about $0.0358 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.