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/jungjaehoon-lifegamez/MAMAWrote 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/mcp/jungjaehoon-lifegamez/mama/claude-code-plugin-mama)<a href="https://agentmods.dev/mcp/jungjaehoon-lifegamez/mama/claude-code-plugin-mama"><img src="https://agentmods.dev/badge/mcp/jungjaehoon-lifegamez/mama/claude-code-plugin-mama/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/mcp/jungjaehoon-lifegamez/mama/claude-code-plugin-mama"><img src="https://agentmods.dev/badge/mcp/jungjaehoon-lifegamez/mama/claude-code-plugin-mama.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mama 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 yesterday.
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
{
"mama": {
"command": "npx",
"args": [
"-y",
"@jungjaehoon/[email protected]"
],
"description": "MAMA - Memory-Augmented MCP Assistant"
}
}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.
- yesterday Changed 44df6414f24a
- 2d ago First seen · 10 lines scan A d43fc913b845
mama is an MCP server published in the GitHub repository jungjaehoon-lifegamez/MAMA (15 stars, last pushed yesterday), 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 2026-10-16.
Other mcp servers, from other repositories
memai
MCP server "memai" as configured in Filipe-Soares-de-Almeida/MemAI. Runs locally from the memai Python package.
distillery-mcp
Persistent shared memory for Claude Code — MCP server with DuckDB vector search, semantic dedup, and ambient intelligence for team knowledge. Runs locally from the distillery-mcp Python package. Needs 2 environment variables to run.
memoryhub
MCP server for persistent memory using Qdrant vector store. Runs locally from the @taraksh011/memoryhub npm package.
inkdex
MCP server that indexes markdown docs and exposes hybrid semantic search for LLM context retrieval. Runs locally from the inkdex npm package.
cozo-memory
Local-first memory system for AI agents with hybrid search and graph reasoning. Runs locally from the cozo-memory npm package.
mcp-working-context-optimizer
MCP server "mcp-working-context-optimizer" as configured in globalpocket/mcp-working-context-optimizer. Runs locally from the mcp-working-context-optimizer Python package.