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/Bumblebiber/hmemWrote 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/bumblebiber/hmem/hmem-mcp)<a href="https://agentmods.dev/mcp/bumblebiber/hmem/hmem-mcp"><img src="https://agentmods.dev/badge/mcp/bumblebiber/hmem/hmem-mcp/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/bumblebiber/hmem/hmem-mcp"><img src="https://agentmods.dev/badge/mcp/bumblebiber/hmem/hmem-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
hmem-mcp 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
{
"hmem-mcp": {
"command": "npx",
"args": [
"-y",
"hmem-mcp"
],
"env": {
"HMEM_STORAGE_DIR": ""
}
}
}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 · 12 lines scan A 56208024a53d
hmem-mcp is an MCP server published in the GitHub repository Bumblebiber/hmem (24 stars, last pushed 3mo 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 2026-08-30.
Other mcp servers, from other repositories
grok-faf-mcp
Persistent project context for xAI Grok. IANA-registered .faf format. Runs locally from the grok-faf-mcp npm package.
umt-hackernews
Read-only Hacker News MCP tools for ranked story lists, keyword search, and discussion threads. Runs locally from the @universal-mcp-toolkit/server-hackernews npm package.
umt-arxiv
Paper discovery and reading-list tools for arXiv. Runs locally from the @universal-mcp-toolkit/server-arxiv npm package.
umt-npm-registry
Package metadata, search, and version tools for the npm registry. Runs locally from the @universal-mcp-toolkit/server-npm-registry npm package.
alice
Alice: the continuity layer for AI agents. Local-first memory with provenance, open loops, resumption, and review-governed writes. Runs locally from the alice-memory Python package.
amnesic
The MCP server with the most ironic name in the registry — persistent semantic memory for your SQL databases. Runs locally from the amnesic Python package.