Safe AI Agent — Guard Checks
A free, read-only MCP server for diagnosing production AI-agent guardrails.
Audit API key permission descriptions for over-privilege risk without accepting real secret values.
Statically scan code snippets for idempotency and duplicate-execution guard signals, returning present/missing signals and a verdict.
Explain known guard patterns such as idempotency keys, approval gates, outboxes, key inventories, circuit breakers, and signed approval links.
Run no network calls and perform no writes.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Safe AI Agent — Guard Checks explain idempotency keys for duplicate agent actions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Safe AI Agent — Guard Checks (free MCP server)
A free, read-only MCP server with three diagnostic tools for people who run AI agents in production. Distilled from the Safe AI Agent Pack — the production guard modules used by the Sage personal agent and the Growl AI marketing SaaS.
No network calls. No writes. Inputs that look like real secrets are refused.
Tools
Tool | What it does |
| Flags over-privileged API keys from their permission descriptions (never pass key values — secret-looking entries are rejected, not stored) |
| Scans a code snippet for the signals that actually stop duplicate execution: idempotency key, server-side store, uniqueness, short-circuit, payload binding, approval separation |
| Explains a production guard pattern — the failure it prevents and its minimal shape ( |
Related MCP server: agent-guard
Install & run
git clone <this repo>
cd safe-agent-mcp
python3 -m venv .venv && .venv/bin/pip install -r requirements.txt
.venv/bin/python safe_agent_mcp.py # stdio transportClaude Desktop / Cursor MCP config:
{
"mcpServers": {
"safe-agent-guard-checks": {
"command": "/path/to/.venv/bin/python",
"args": ["/path/to/safe_agent_mcp.py"]
}
}
}Test
.venv/bin/python test_server.py # in-memory client; calls every toolThe full pack
This free server is the diagnostic front door. The production modules —
SQLite idempotency store, @once decorator, approval outbox with HMAC-signed
approval links, the token-privilege inventory script, 18 regression tests and
the 100 production-traps catalog — ship in the
Safe AI Agent Pack ($69 / team $199).
License
MIT for this free server. The paid pack has its own commercial license.
Get the kit
Starter Kit ($19) — the 24-traps checklist + guard-patterns guide bundle: https://whop.com/growl-ai/safe-ai-agent-starter-kit-guardrails-for-ai-agents
Full Pack ($69 / team $199) — 100-traps catalog, working modules, sabotage-test playbook: https://growl-ai.com/store/en
Background reading: Idempotency Keys, Explained (dev.to)
Available Tools
3 toolsaudit_api_keysAudit Api KeysA
Audit API keys for over-privilege using permission descriptions only.
Pass entries like {"name": "stripe-main", "service": "Stripe", "scopes": ["charges:write", "refunds:write"]}. NEVER pass actual key values — entries that look like secrets are rejected, not stored. Returns a per-key risk level with reasons and a summary count.
Inputs: keys (required). Returns: object
check_idempotency_patternCheck Idempotency PatternA
Check a code snippet for the signals that stop duplicate execution.
Paste the function that performs the side effect (sending, charging, writing). Returns which guard signals are present, which are missing, and a plain verdict. Read-only static check — the code is not executed.
Inputs: code (required). Returns: object
explain_guard_patternExplain Guard PatternA
Explain one production guard pattern: what failure it prevents and its minimal shape.
Known patterns: idempotency_key, approval_gate, outbox, key_inventory, circuit_breaker, signed_approval_link.
Inputs: pattern (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools occupy genuinely different modes: auditing a config artifact (API key scopes), statically checking a code snippet, and explaining a concept. The one soft edge is between check_idempotency_pattern and explain_guard_pattern, since 'idempotency_key' is also one of the explainable patterns, so an agent asking about idempotency could plausibly reach for either first.
All three follow a clean verb_noun snake_case pattern (audit_api_keys, check_idempotency_pattern, explain_guard_pattern) with unambiguous, domain-specific nouns. The verbs also accurately signal the mode of each tool: audit vs check vs explain.
Three tools is on the thin side but defensible for a tightly scoped 'guard checks' server where each tool maps to one clear input type (key entries, code, pattern name). No padding or redundancy, though the surface feels minimal enough that additional coverage seems intended rather than optional.
The tool set is asymmetric: explain_guard_pattern advertises six patterns (idempotency_key, approval_gate, outbox, key_inventory, circuit_breaker, signed_approval_link) but only idempotency has a corresponding verification tool, and key_inventory is only partly covered by audit_api_keys. An agent can learn about approval gates and outboxes but has no way to check them, creating dead ends in the advertised workflow.
Maintenance
Related MCP Connectors
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Agent security: prompt injection, PII & secret scans, TLS/header/CORS audits, MCP checks. Free.
Checks AI-written code for leaked keys and made-up packages, on your machine. Never uploads code.
Free pre-execution contract checks for AI agents: preflight, control-plane scans, EAS anchors.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceLocal-first security check for AI coding agents — finds hardcoded secrets, exposed .env files, git-history leaks and vulnerable dependencies (OSV), entirely on your machine. Ask your agent "is this safe to ship?" and get a Launch Readiness score with a fix for every finding.MIT
agent-guardprivate
AlicenseAqualityCmaintenanceSafety checks an agent runs before it acts — flags malicious packages, destructive shell commands, secret leaks, and web-backend holes before execution.828 PyPIMIT- AlicenseNot gradedqualityCmaintenanceIt lets clients request design-time audits of Python and TypeScript agent applications for defects such as unbounded loops, ungated destructive actions, weak argument validation, insufficient run budgets, absent resiliency controls, overlooked evals, and poor observability. Findings include supporting evidence and feed an approval-driven mechanism for reviewing proposed fixes without mutating the original source.MIT
- AlicenseNot gradedqualityBmaintenanceA read-only MCP server that lets agents scan a project's AI agent setup — Claude Code, Codex, Cursor, MCP servers and instruction files — and surface security findings such as the lethal trifecta, broad permissions, exposed secrets and unpinned packages.57 npmMIT