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.
npx agentmods add mcp/raya-ac/engram/engram-memory-systemgit clone --depth 1 https://github.com/raya-ac/engramGrade A, and why
engram-memory-system 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
{ "engram-memory-system": { "command": "uvx", "args": [ "engram-memory-system" ] } }
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 · 8 lines scan A f40f47f1d19e
engram-memory-system is an MCP server published in the GitHub repository raya-ac/engram (2 stars, last pushed 4mo 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.
Other mcp servers, from other repositories
yantrikdb-mcp
YantrikDB — Cognitive memory for AI agents. Persistent semantic recall, knowledge graph, contradiction detection, and procedural learning. Ships as embeddable engine, network database, or MCP server. Runs locally from the yantrikdb-mcp Python package.
memx
MCP server "memx" as configured in NeoLi00/memX. Runs ${CLAUDE_PLUGIN_ROOT}/dist/.runtime/src/bin/memx-mcp.mjs with node. Needs 3 environment variables to run.
midas
MCP server for Midas — local-first, source-traceable agent memory with no LLM at ingest. Runs locally from the midas-memory-mcp Python package. Needs 4 environment variables to run.
trinity-memory
Trinity v8.2.0: Memory Operating System — Multi-Agent Shared Memory, 50-Layer Guardian Chain, 129-Paper Brain-Inspired Alignment, GraphQL API, Raft Cluster, BM25+Jieba Chinese Retrieval. Runs locally from the trinity-memory Python package.
mnemon-memory
Universal long-term memory layer for AI agents via MCP. Runs locally from the mnemon-memory Python package.
velesdb-memory
MCP server "velesdb-memory" as configured in cyberlife-coder/VelesDB. Launched with https://github.com/cyberlife-coder/VelesDB/releases/download/velesdb-memory-v0.9.