agentmods.dev

mcp-memos

mcp-memos is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from jkawamoto/mcp-memos. Its token cost is not measured, scanned A, original, MIT.

An MCP server that connects an AI coding agent to a Memos notes service, using its API address and access token.

In plain words
What is it for?
It is for connecting an agent to a Memos installation at a chosen address with an API token. The input does not specify which note operations are available.
Why use it?
It removes the need to build a separate connection between the agent and Memos. The server cannot run without the two required environment variables.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 0repo 5mo ago A scan tokens not measured original MIT archived

Good fit It is for connecting an agent to a Memos installation at a chosen address with an API token. The input does not specify which note operations are available.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/jkawamoto/mcp-memos/mcp-memos

Installing this writes the configuration, not the program: `https://github.com/jkawamoto/mcp-memos/releases/download/v0.1.0/mcp-memos.mcpb` has to be on your PATH already, or the server will not start.

View source ↗ jkawamoto/mcp-memos
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.

Clone the repo
git clone --depth 1 https://github.com/jkawamoto/mcp-memos

Installing this writes the configuration, not the program: `https://github.com/jkawamoto/mcp-memos/releases/download/v0.1.0/mcp-memos.mcpb` has to be on your PATH already, or the server will not start.

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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-memos

README.md
[![agentmods](https://agentmods.dev/badge/mcp/jkawamoto/mcp-memos/mcp-memos/github.svg)](https://agentmods.dev/mcp/jkawamoto/mcp-memos/mcp-memos)
Your own site
<a href="https://agentmods.dev/mcp/jkawamoto/mcp-memos/mcp-memos"><img src="https://agentmods.dev/badge/mcp/jkawamoto/mcp-memos/mcp-memos/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.

agentmods 80×15 button for mcp-memos

Your own site · 80×15
<a href="https://agentmods.dev/mcp/jkawamoto/mcp-memos/mcp-memos"><img src="https://agentmods.dev/badge/mcp/jkawamoto/mcp-memos/mcp-memos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

mcp-memos 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 2mo 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.

server.json · 10 lines

What it actually says

{
  "mcp-memos": {
    "command": "https://github.com/jkawamoto/mcp-memos/releases/download/v0.1.0/mcp-memos.mcpb",
    "args": [],
    "env": {
      "MEMOS_API_ENDPOINT": "localhost:5230",
      "MEMOS_API_TOKEN": ""
    }
  }
}
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. 2mo ago First seen · 10 lines scan A 3c609a03fe2b

Subscribe to this mod's changes

mcp-memos is an MCP server published in the GitHub repository jkawamoto/mcp-memos (0 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.

Memory and contextmcp-servermemos
Related

mcp-memos compared with mcp servers from other repositories

mcp-memos next to 6 mcp servers from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-memosjkawamoto/mcp-memosMCP server05mo agoMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
memorixAVIDS2/memorixMCP server9193d agoApache-2.0A—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
prism-mcpdcostenco/prism-coderMCP server156todayApache-2.0A—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
mcp-neo4j-memoryneo4j-contrib/mcp-neo4jMCP server9902mo agoMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
hypermnesia-mcpcdeust/CortexMCP server76yesterdayMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
ai-memoryalphaonedev/ai-memory-mcpMCP server56todayApache-2.0A—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
neverinfamous-memory-journal-mcpneverinfamous/memory-journal-mcpMCP server205d agoMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode