Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add xiaojiou176-open/notes-recover/plugin install notes-recover-claude-pluginWrote 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/xiaojiou176-open/notes-recover/noteyard-claude-plugin-notes-recover)<a href="https://agentmods.dev/mcp/xiaojiou176-open/notes-recover/noteyard-claude-plugin-notes-recover"><img src="https://agentmods.dev/badge/mcp/xiaojiou176-open/notes-recover/noteyard-claude-plugin-notes-recover/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/xiaojiou176-open/notes-recover/noteyard-claude-plugin-notes-recover"><img src="https://agentmods.dev/badge/mcp/xiaojiou176-open/notes-recover/noteyard-claude-plugin-notes-recover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
notes-recover 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 10d 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
{
"notes-recover": {
"command": "${CLAUDE_PLUGIN_ROOT}/bin/notes-recover-mcp",
"env": {
"NOTES_RECOVER_REPO_ROOT": "${NOTES_RECOVER_REPO_ROOT}",
"NOTES_RECOVER_CASE_DIR": "${NOTES_RECOVER_CASE_DIR}",
"NOTES_RECOVER_PYTHON": "${NOTES_RECOVER_PYTHON}"
}
}
}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.
- 10d ago First seen · 10 lines scan A ebce66ccd72e
notes-recover is an MCP server published in the GitHub repository xiaojiou176-open/notes-recover (2 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
knowns
MCP server "knowns" as configured in knowns-dev/knowns. Launched with knowns mcp --stdio.
memorywhale
MCP server "memorywhale" as configured in wuisabel-gif/MemWhale. Launched with mw-mcp.
remem
Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite. Runs locally from the @remem-ai/remem npm package.
nexusmem
Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP. Runs locally from the nexusmem npm package.
atomicmemory
MCP server exposing AtomicMemory's ingest / search / package tools to any MCP-compatible agent. Runs locally from the @atomicmemory/mcp-server npm package. Needs 7 environment variables to run.
mitos
Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents. Runs locally from the mitos-adr Python package.