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/danielsimonjr/memory-mcp/settingsgit clone --depth 1 https://github.com/danielsimonjr/memory-mcpGrade A, and why
memory-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 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"project": {
"name": "MCP Servers Collection",
"description": "Collection of 14 specialized Model Context Protocol servers (10 local + 4 global packages)",
"type": "multi-server-repository"
},
"defaultServer": "memory-mcp",
"enabledServers": [
"deepthinking-mcp",
"markitdown-mcp",
"math-mcp",
"memory-mcp",
"fzf-mcp",
"sequential-thinking-mcp",
"playwright",
"time",
"windows-mcp"
],
"disabledServers": [
"everything-mcp",
"substack-mcp"
],
"platformSpecific": {
"windows": {
"required": ["everything-mcp"],
"optional": []
},
"crossPlatform": [
"deepthinking-mcp",
"fzf-mcp",
"markitdown-mcp",
"math-mcp",
"memory-mcp",
"fermat-mcp",
"remember-mcp",
"substack-mcp"
]
},
"serverCategories": {
"reasoning": ["deepthinking-mcp", "sequential-thinking-mcp"],
"mathematics": ["math-mcp", "fermat-mcp"],
"memory": ["memory-mcp", "remember-mcp"],
"search": ["everything-mcp", "fzf-mcp"],
"conversion": ["markitdown-mcp"],
"integration": ["substack-mcp"],
"automation": ["playwright", "windows-mcp"],
"utilities": ["time"]
},
"buildRequirements": {
"typescript": {
"servers": ["deepthinking-mcp", "math-mcp", "memory-mcp", "substack-mcp"],
"buildCommand": "npm run build",
"entryPoint": "dist/"
},
"javascript": {
"servers": ["everything-mcp", "fzf-mcp"],
"buildCommand": null,
"entryPoint": "index.js"
},
"python": {
"servers": ["fermat-mcp", "markitdown-mcp", "remember-mcp", "time"],
"buildCommand": null,
"entryPoint": "server.py",
"pythonVersion": "3.10+"
},
"globalPackages": {
"servers": ["sequential-thinking-mcp", "playwright", "windows-mcp"],
"note": "Installed globally via npm install -g <package>"
}
},
"dependencies": {
"external": {
"everything-mcp": {
"name": "Everything",
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 · 154 lines scan A a79b8d9a1b5d
memory-mcp is a settings file published in the GitHub repository danielsimonjr/memory-mcp (3 stars, last pushed 2d 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 2026-08-31.
Other settings, from other repositories
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
superset
Agent settings declaring 1 hook event (PreToolUse).
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).