agentmods.dev

ai-agent-firewall

ai-agent-firewall is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from lucaslubi/fidacy-mcp. Its token cost is not measured, scanned A, original, Apache-2.0.

A locally running safety service that watches an AI agent’s actions and checks money-moving actions before they happen.

In plain words
What is it for?
Use it to review agent actions and require a verified approval before payment or other financial operations.
Why use it?
It helps catch risky payments, such as a wrong recipient, an amount above a limit, or a repeated invoice, before money is sent. Its decisions can be checked independently.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 1repo 1mo ago A scan tokens not measured original Apache-2.0

Good fit Use it to review agent actions and require a verified approval before payment or other financial operations.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/lucaslubi/fidacy-mcp/ai-agent-firewall
View source ↗ lucaslubi/fidacy-mcp fidacy.com
Install

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.

Clone the repo
git clone --depth 1 https://github.com/lucaslubi/fidacy-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-agent-firewall

README.md
[![agentmods](https://agentmods.dev/badge/mcp/lucaslubi/fidacy-mcp/ai-agent-firewall/github.svg)](https://agentmods.dev/mcp/lucaslubi/fidacy-mcp/ai-agent-firewall)
Your own site
<a href="https://agentmods.dev/mcp/lucaslubi/fidacy-mcp/ai-agent-firewall"><img src="https://agentmods.dev/badge/mcp/lucaslubi/fidacy-mcp/ai-agent-firewall/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-agent-firewall

Your own site · 80×15
<a href="https://agentmods.dev/mcp/lucaslubi/fidacy-mcp/ai-agent-firewall"><img src="https://agentmods.dev/badge/mcp/lucaslubi/fidacy-mcp/ai-agent-firewall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

ai-agent-firewall 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 10d 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.

server.json · 14 lines

What it actually says

{
  "ai-agent-firewall": {
    "command": "npx",
    "args": [
      "-y",
      "@fidacy/mcp"
    ],
    "env": {
      "FIDACY_ENGINE_API_KEY": "",
      "FIDACY_OPERATOR_EMAIL": "",
      "FIDACY_MODE": ""
    }
  }
}
Changes

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.

  1. 10d ago First seen · 14 lines scan A 0d3259237418

Subscribe to this mod's changes

ai-agent-firewall is an MCP server published in the GitHub repository lucaslubi/fidacy-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. 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.

Securityai-agentsbitcoined25519firewallmcpmcp-server
Related

Other mcp servers, from other repositories

hemmabo

MCP server "hemmabo", hosted remotely at www.hemmabo.com, as configured in HemmaBo-se/hemmabo-mcp-server.

HemmaBo-se/hemmabo-mcp-server · not measured

hemmabo-mcp-server

Host-owned vacation-rental direct booking via VRP. Signed offers, 0% commission. Not an OTA. Remote server at www.hemmabo.com.

HemmaBo-se/hemmabo-mcp-server · not measured

otskit-mcp

Stamp, upgrade, and verify Bitcoin timestamps via AI agents. No API keys required. Runs locally from the @otskit/mcp npm package.

OTSkit/OTSkit-MCP · not measured

ordinals

Bitcoin Ordinals MCP Server — inscriptions, runes, BRC-20, collections & rare sats. Runs locally from the ordinals-mcp npm package. Needs 3 environment variables to run.

ExpertVagabond/ordinals-mcp · not measured

sophos-firewall-mcp-server

MCP server "sophos-firewall-mcp-server" as configured in jelmervdm/sophos-firewall-mcp. Runs locally from the sophos-firewall-mcp-server Python package.

jelmervdm/sophos-firewall-mcp · not measured

netdefense-mcp

MCP server "netdefense-mcp" as configured in netdefense-io/NDCLI. Launched with https://github.com/netdefense-io/ndcli-releases/releases/download/v1.29.2/netdef. Needs 1 environment variable to run.

netdefense-io/NDCLI · not measured