A persistent memory add-on for an AI agent that can store, search, and recall knowledge between sessions. Persistent memory means saved information remains available after a conversation ends.

Use it to save useful knowledge, search past information, and bring earlier context into later conversations.

It reduces the need to repeat project context, decisions, or facts in every new session.

mnemo-mcp — Plugin for Claude Code by expandingideas-ai: A persistent memory add-on for an AI agent that…

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.

Claude Code

/plugin marketplace add expandingideas-ai/Mnemo-MCP

agentmods

npx agentmods add plugins/expandingideas-ai/mnemo-mcp/mnemo-mcp

Clone the repo

git clone --depth 1 https://github.com/expandingideas-ai/Mnemo-MCP

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/expandingideas-ai/mnemo-mcp/mnemo-mcp.svg)](https://agentmods.dev/plugins/expandingideas-ai/mnemo-mcp/mnemo-mcp)

Your own site

<a href="https://agentmods.dev/plugins/expandingideas-ai/mnemo-mcp/mnemo-mcp"><img src="https://agentmods.dev/badge/plugins/expandingideas-ai/mnemo-mcp/mnemo-mcp.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 5 skills, 2 hooks, 1 MCP server cost 249 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin 95% copy Near-identical to another mod in the catalogue.

Security

Grade A, and why

mnemo-mcp 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 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.

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.

Origin

This is a copy

95% identical to mnemo-mcp — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude-plugin/plugin.json · 58 lines

What it actually says

{
  "name": "mnemo-mcp",
  "description": "Persistent AI memory — store, search, and recall knowledge across sessions",
  "version": "2.3.0-beta.19",
  "userConfig": {
    "JINA_AI_API_KEY": {
      "type": "string",
      "title": "Jina AI API key (optional)",
      "description": "Optional cloud reranker key. https://jina.ai/api-dashboard/",
      "sensitive": true,
      "required": false
    },
    "GEMINI_API_KEY": {
      "type": "string",
      "title": "Gemini API key (optional)",
      "description": "Optional cloud embedding + LLM. Free tier available. https://aistudio.google.com/apikey",
      "sensitive": true,
      "required": false
    },
    "OPENAI_API_KEY": {
      "type": "string",
      "title": "OpenAI API key (optional)",
      "description": "Optional cloud embedding + LLM (lower priority than Gemini). https://platform.openai.com/api-keys",
      "sensitive": true,
      "required": false
    },
    "COHERE_API_KEY": {
      "type": "string",
      "title": "Cohere API key (optional)",
      "description": "Optional cloud embedding + reranking. https://dashboard.cohere.com/api-keys",
      "sensitive": true,
      "required": false
    }
  },
  "author": {
    "name": "n24q02m",
    "url": "https://github.com/n24q02m"
  },
  "homepage": "https://github.com/n24q02m/mnemo-mcp",
  "mcpServers": {
    "mnemo": {
      "command": "uvx",
      "args": [
        "--python",
        "3.13",
        "mnemo-mcp"
      ],
      "env": {
        "MCP_TRANSPORT": "stdio",
        "JINA_AI_API_KEY": "${user_config.JINA_AI_API_KEY}",
        "GEMINI_API_KEY": "${user_config.GEMINI_API_KEY}",
        "OPENAI_API_KEY": "${user_config.OPENAI_API_KEY}",
        "COHERE_API_KEY": "${user_config.COHERE_API_KEY}"
      }
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 5 skills, 2 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 249 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

4d ago First seen · 58 lines scan A 317211b28a33

Subscribe to this mod's changes

mnemo-mcp is a plugin published in the GitHub repository expandingideas-ai/Mnemo-MCP (0 stars, last pushed 2mo ago), licensed MIT. 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. It is 95% identical to mnemo-mcp, differing in 2 lines, and is treated as a copy.

Memory and context

mnemo-mcp

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

This is a copy

What it actually says

What it installs

What this file has done since we first saw it

Other plugins, from other repositories

knowledge-and-memory

@tekmidian/pai

claude-mega-brain

tree-ring-memory

vault-template

compact-manager