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/irisxc4/memoryguardWrote 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/irisxc4/memoryguard/memoryguard)<a href="https://agentmods.dev/mcp/irisxc4/memoryguard/memoryguard"><img src="https://agentmods.dev/badge/mcp/irisxc4/memoryguard/memoryguard/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/irisxc4/memoryguard/memoryguard"><img src="https://agentmods.dev/badge/mcp/irisxc4/memoryguard/memoryguard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
memoryguard 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
{
"memoryguard": {
"command": "uvx",
"args": [
"agent-memguard"
],
"env": {}
}
}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 · 9 lines scan A ac19810eda07
memoryguard is an MCP server published in the GitHub repository irisxc4/memoryguard (3 stars, last pushed 1mo 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
deja-vu
Local memory for coding agents: search, MCP recall, auto-recall, secret redaction, SSH sync. Runs locally from the @vshulcz/deja-vu npm package.
goodmemory
Durable user/project memory for MCP clients: recall context and remember selected facts. Runs locally from the goodmemory npm package.
infinity-context
MCP server "infinity-context" as configured in 777genius/infinity-context. Launched with ${workspaceFolder}/plugins/infinity-context-agent-plugin-cursor-workspace/bin/in. Needs 13 environment variables to run.
arkhive
ArkHive MCP — governed, tamper-evident memory for AI agents. Tell your AI to check the ArkHive. (Formerly published as humane-intelligence.). Runs locally from the arkhive-mcp Python package.
snipara
Hosted MCP for source-backed project context, memory, code impact, and agent workflow continuity. Remote server at api.snipara.com.
mnemic-memory
MCP server "mnemic-memory" as configured in dongtang3/mnemic. Launched with /bin/bash ./scripts/run-agent-memory-mcp.sh. Needs 1 environment variable to run.