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.
/plugin marketplace add NeuralNexusNote/n3mcmcp-litenpx agentmods add plugins/neuralnexusnote/n3mcmcp-lite/n3mc-workingmemorygit clone --depth 1 https://github.com/NeuralNexusNote/n3mcmcp-liteGrade A, and why
n3mc-workingmemory 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 2d 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": "n3mc-workingmemory",
"description": "Ephemeral (7-day TTL) hybrid vector + BM25 memory server for Claude Code, backed by Redis Stack. Multilingual out of the box (NFKC + CJK / Hangul / Thai / Lao / Myanmar / Khmer bigram + diacritic fold). Prerequisites: (1) Redis Stack running on localhost:6379 (docker run -d --name redis-stack -p 6379:6379 redis/redis-stack-server:latest) and (2) uv installed on PATH (https://docs.astral.sh/uv/).",
"version": "1.9.1",
"author": {
"name": "NeuralNexusNote",
"email": "[email protected]"
},
"homepage": "https://github.com/NeuralNexusNote/n3mcmcp-lite",
"repository": "https://github.com/NeuralNexusNote/n3mcmcp-lite",
"license": "Apache-2.0",
"keywords": ["memory", "rag", "redis", "vector-search", "bm25", "embedding", "ephemeral", "multilingual", "japanese", "cjk"],
"mcpServers": {
"n3mc-workingmemory": {
"command": "uvx",
"args": ["--from", "n3memorycore-mcp-lite", "n3mc-workingmemory"]
}
}
}
What it installs
The manifest is a name and a version. 1 hook travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
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.
- 2d ago First seen · 20 lines scan A 09de8084ab4b
n3mc-workingmemory is a plugin published in the GitHub repository NeuralNexusNote/n3mcmcp-lite (0 stars, last pushed 3mo ago), 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 2026-08-31.
Other plugins, from other repositories
redis-development
Redis development best practices — data structures, query engine, vector search, caching, and performance optimization.
upstash
Agent skills for all Upstash SDKs — Redis, QStash, Workflow, Box, Ratelimit, Vector, and Search.
queue-aiops
Governed redis + rabbitmq ops: memory/latency/backlog/churn RCA, policies. 28 tools.
redis-channel
Claude Code channel that bridges sessions to external systems over Redis Streams. Router-agnostic: pair with any router implementation that speaks the protocol.
luxor-database-pro
Professional database engineering skills covering PostgreSQL, SQLAlchemy, Alembic, pandas, Redis, vector databases, and database patterns.
database
Access MySQL, PostgreSQL, SQLite databases, and Redis key-value stores via CLI for querying, schema/key exploration, and data management.