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/BMC-INC/Iron-memInstalling this writes the configuration, not the program: `~/.ironmem/bin/ironmem` has to be on your PATH already, or the server will not start.
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.
[](https://agentmods.dev/mcp/bmc-inc/iron-mem/ironmem)<a href="https://agentmods.dev/mcp/bmc-inc/iron-mem/ironmem"><img src="https://agentmods.dev/badge/mcp/bmc-inc/iron-mem/ironmem/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/bmc-inc/iron-mem/ironmem"><img src="https://agentmods.dev/badge/mcp/bmc-inc/iron-mem/ironmem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ironmem 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 1mo 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
{
"ironmem": {
"command": "~/.ironmem/bin/ironmem",
"args": [
"mcp"
]
}
}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.
- 1mo ago First seen · 8 lines scan A 16bd16bec6e9
ironmem is an MCP server published in the GitHub repository BMC-INC/Iron-mem (5 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 2026-08-31.
Other mcp servers, from other repositories
memorix
MCP server "memorix" as configured in AVIDS2/memorix. Launched with memorix serve --mode lite.
memorix
Local-first project memory with legacy MCP and 2026 discovery compatibility. Runs locally from the memorix npm package.
ai-mind-map
AI Mind Map — MCP server that reduces AI coding agent token usage by 80-99% through persistent codebase memory, knowledge graphs, and intelligent context management. Runs locally from the ai-mind-map npm package.
coster
Universal context persistence layer for AI coding assistants. Runs locally from the coster npm package.
symbiote
Symbiote bonds with your AI tools — giving them memory, context, and your coding DNA. Runs locally from the symbiote-cli npm package.
knowns
MCP server "knowns" as configured in knowns-dev/knowns. Launched with knowns mcp --stdio.