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/bulbulbul86/codex-native-memory/codex_native_memorygit clone --depth 1 https://github.com/BulbuLbul86/codex-native-memoryGrade A, and why
codex_native_memory 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 yesterday.
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
{
"codex_native_memory": {
"command": "powershell.exe",
"cwd": ".",
"args": [
"-NoProfile",
"-ExecutionPolicy",
"Bypass",
"-File",
"./scripts/run-mcp.ps1"
]
}
}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.
- yesterday First seen · 13 lines scan A 730c5fed7fad
codex_native_memory is an MCP server published in the GitHub repository BulbuLbul86/codex-native-memory (0 stars, last pushed 2mo 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
image_context_runtime
MCP server "imagecontextruntime" as configured in shixinnt/codex-image-context-runtime. Runs ./mcp/server.mjs with node.
mooncite
MCP server "mooncite" as configured in WhenMoon-afk/claude-memory-mcp. Runs dist/cli.js with node.
wakeflow
MCP server "wakeflow" as configured in GxFn/Wakeflow. Launched with ${CLAUDE_PLUGIN_ROOT}/bin/wakeflow-mcp.
tg-recall
MCP server "tg-recall" as configured in Rerowros/tg-recall. Runs locally from the tg-recall Python package.
icon_svg_select
MCP server "iconsvgselect" as configured in tetracoralla/armorial. Runs ./dist/adapters/mcp.js with node.
agent-kudos
Local-first recognition and accomplishment infrastructure for AI agents. Runs locally from the agent-kudos npm package.