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/LeandroPG19/MemorysWrote 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/leandropg19/memorys/memory-industry)<a href="https://agentmods.dev/mcp/leandropg19/memorys/memory-industry"><img src="https://agentmods.dev/badge/mcp/leandropg19/memorys/memory-industry/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/leandropg19/memorys/memory-industry"><img src="https://agentmods.dev/badge/mcp/leandropg19/memorys/memory-industry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
memory-industry 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 22d 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
{
"memory-industry": {
"command": "npx",
"args": [
"-y",
"memory-industry"
],
"env": {
"DATABASE_URL": "",
"CUBA_PROJECT_FILTER": "",
"CUBA_SYNC_DIR": "",
"CUBA_JUDGE": "",
"CUBA_JUEZ_CLI": "",
"CUBA_JUEZ_MODEL": "",
"CUBA_REM_RELATION_BATCH": "",
"CUBA_RERANKER_PATH": "",
"CUBA_RERANK_FIXED_SHAPE": ""
}
}
}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.
- 22d ago First seen · 20 lines scan A 36f4b7626086
memory-industry is an MCP server published in the GitHub repository LeandroPG19/Memorys (30 stars, last pushed 2d ago), licensed Apache-2.0. 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 2026-09-24.
Other mcp servers, from other repositories
projectmem
Coding agent memory — local-first memory and judgment for AI coding agents. One MCP server for every project; warns before repeating failed fixes. Runs locally from the projectmem Python package.
memory-os-ai
MCP server "memory-os-ai" as configured in romainsantoli-web/Memory-os-ai. Runs memory_os_ai.server with /Users/romain/Memory-os-ai/.venv/bin/python. Needs 5 environment variables to run.
memento-context
MCP server "memento-context" as configured in FranBarInstance/memento-context. Runs locally from the memento-context Python package.
better-memory-mcp
MCP server "better-memory-mcp" as configured in guinacio/better-memory-mcp. Runs locally from the @guinacio/better-memory-mcp npm package.
claude-dejavu
MCP server "claude-dejavu" as configured in HthSolid/claude-dejavu. Runs ${CLAUDE_PLUGIN_ROOT}/bin/claude-dejavu-mcp.py with python.
task-orchestrator
MCP server "task-orchestrator" as configured in jpicklyk/task-orchestrator. Runs in Docker (ghcr.io/jpicklyk/task-orchestrator:latest). Needs 6 environment variables to run.