Safe Agent Mcp

io.github.naoanaoPublished by GitHub account naoanaov0.1.0Updated Nov 3, 2026

Audit API-key privileges, check idempotency patterns, explain AI-agent guard patterns. Read-only.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A local, read-only MCP server with three diagnostic tools that audit API-key privileges, check idempotency guards in code, and explain production guard…

What you can do
  • Audit API keys for over-privilege from permission descriptions only, returning a per-key risk level
  • Check a code snippet for the signals that prevent duplicate execution and report which are missing
  • Explain a named production guard pattern, the failure it prevents and its minimal shape
When to use it
Useful when you run AI agents or side-effecting code in production and want a quick, read-only second opinion on key scopes, duplicate-execution guards, or which guard pattern fits a failure you are trying to prevent.
Requirements
Runs as a local Python process over stdio; the README describes cloning the repository, creating a virtual environment, installing requirements, and pointing the client config at the Python interpreter and script. No network calls, accounts, API keys or environment variables are declared.
Before you install
The tools are described as read-only with no writes and no network calls, and inputs that look like real secrets are refused; still, never paste actual key values, only permission descriptions. The README promotes paid starter kits and a full pack, so expect commercial upsell alongside the free tools.

Installation

In SourceWeft

  1. Open Safe Agent Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

ToolWhat it does
audit_api_keysFlags over-privileged API keys from their permission descriptions (never pass key values — secret-looking entries are rejected, not stored)
check_idempotency_patternScans a code snippet for the signals that actually stop duplicate execution: idempotency key, server-side store, uniqueness, short-circuit, payload binding, approval separation
explain_guard_patternExplains a production guard pattern — the failure it prevents and its minimal shape (idempotency_key, approval_gate, outbox, key_inventory, circuit_breaker, signed_approval_link)

Install & run

bash
git clone <this repo>cd safe-agent-mcppython3 -m venv .venv && .venv/bin/pip install -r requirements.txt.venv/bin/python safe_agent_mcp.py   # stdio transport

Claude Desktop / Cursor MCP config:

json
{  "mcpServers": {    "safe-agent-guard-checks": {      "command": "/path/to/.venv/bin/python",      "args": ["/path/to/safe_agent_mcp.py"]    }  }}

Test

bash
.venv/bin/python test_server.py   # in-memory client; calls every tool

The 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

Source: README.md at commit 0ef9c02

Tools

3

audit_api_keys

Audit Api Keys

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.

Parameterskeysrequired

check_idempotency_pattern

Check Idempotency Pattern

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.

Parameterscoderequired

explain_guard_pattern

Explain Guard Pattern

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.

Parameterspatternrequired

Version history

1
  1. v0.1.0LatestOct 29, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts