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 settings/jleechanorg/mcp_mail/settingsgit clone --depth 1 https://github.com/jleechanorg/mcp_mailGrade A, and why
mcp_mail 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"_comment": "Run ./scripts/integrate_claude_code.sh to generate auth token and embed it in headers (recommended)",
"mcpServers": {
"mcp-agent-mail": {
"type": "http",
"url": "http://127.0.0.1:8765/mcp/",
"core": true,
"headers": {
"_note": "Authentication required - run ./scripts/integrate_claude_code.sh to embed token"
},
"options": {
"timeoutSeconds": 180,
"initTimeoutSeconds": 30
}
}
},
"hooks": {
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "bash -lc 'repo_root=\"$(git rev-parse --show-toplevel 2>/dev/null || pwd)\"; if [[ -f \"$repo_root/scripts/auto_register_agent.sh\" ]]; then \"$repo_root/scripts/auto_register_agent.sh\" --program claude-code --model sonnet --nonfatal --force-reclaim; fi'"
}
]
}
],
"PreToolUse": [],
"PostToolUse": []
},
"_exampleHooks": {
"_instructions": "Uncomment and customize these hooks after registering your project and agent. If your server requires auth, generate a local config with an embedded token via ./scripts/integrate_claude_code.sh (recommended) instead of committing secrets.",
"SessionStart_example": [
{
"hooks": [
{ "type": "command", "command": "uv run python -m mcp_agent_mail.cli file_reservations active YOUR_PROJECT_NAME" },
{ "type": "command", "command": "uv run python -m mcp_agent_mail.cli acks pending YOUR_AGENT_NAME --limit 20" }
]
}
],
"PreToolUse_example": [
{
"matcher": "Edit",
"hooks": [
{ "type": "command", "command": "uv run python -m mcp_agent_mail.cli file_reservations soon YOUR_PROJECT_NAME --minutes 10" }
]
}
],
"PostToolUse_example": [
{
"matcher": "mcp__mcp-agent-mail__send_message",
"hooks": [
{ "type": "command", "command": "uv run python -m mcp_agent_mail.cli list-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.
- 2d ago First seen · 64 lines scan A f84b464f075f
mcp_mail is a settings file published in the GitHub repository jleechanorg/mcp_mail (11 stars, last pushed 16d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 settings, from other repositories
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
claude-cookbooks
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.
electron
Agent settings declaring 17 allowed tools.
uv
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
ui-ux-pro-max-skill
Agent settings declaring 7 allowed tools.