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.
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.
git 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/plugins/doobidoo/mcp-memory-service/claude-hooks)<a href="https://agentmods.dev/plugins/doobidoo/mcp-memory-service/claude-hooks"><img src="https://agentmods.dev/badge/plugins/doobidoo/mcp-memory-service/claude-hooks/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.
<a href="https://agentmods.dev/plugins/doobidoo/mcp-memory-service/claude-hooks"><img src="https://agentmods.dev/badge/plugins/doobidoo/mcp-memory-service/claude-hooks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-memory-service 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 5d 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.
What it actually says
{
"name": "mcp-memory-service",
"version": "1.1.0",
"description": "Automatic memory capture and injection for Claude Code via MCP Memory Service",
"author": {
"name": "doobidoo"
},
"homepage": "https://github.com/doobidoo/mcp-memory-service",
"mcpServers": "./.mcp.json",
"hooks": "./.claude-plugin/hooks.json"
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 68 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed a220aadaea3a
- 15d ago Changed f47cb8d342c5
- 1mo ago Changed 732e199c286e
- 1mo ago First seen · 12 lines scan A d3646854daea
mcp-memory-service is a plugin published in the GitHub repository doobidoo/mcp-memory-service (2,021 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
compartment
Encrypted, fully offline memory for Claude Code: one vault on your machine, shared with Claude Desktop, Cursor, Hermes and any other MCP client. Adds 14 memory tools and the /compartmentalize skill. Requires pip install compartment && compartment init first (the vault passphrase is yours to choose).
compartment
Encrypted, fully offline long-term memory for Gemini CLI. One vault on your machine, shared by every MCP client. Requires pip install compartment && compartment init first.
palaia-memory
Makes an agent use palaia's shared memory without being told, and work alongside other agent sessions: when to recall, how to resume work, what deserves capturing, and when to register, check in and reply. Also walks someone through installing palaia itself, step by step.
memorizz
Durable, searchable project memory for Claude Code, shared with Codex and your MemoRizz agents, through MemoRizz's MCP server.
session-recall
Shared semantic recall over local Claude Code, Codex, and Cursor history. Bundles MCP search tools, deep recall, guided setup, and a background freshness hook.
codealive
CodeAlive context engine for semantic code search and AI-powered codebase Q&A. Enables AI coding agents to understand entire codebases beyond just open files — search across all indexed repositories, trace cross-service dependencies, discover usage patterns, and get synthesized answers to architectural questions.…