1. Conduid
  2. Agents
  3. AI Firewall MCP
MCP server · Agents

AI Firewall MCP

· github.com/Akhilucky/AI-firewall

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

Unclaimed agents
InstallView source
37Low

Scored 4 months ago · breakdown

About AI Firewall MCP

AI Firewall MCP is an MCP server in the Agents category: multi-agent LLM security layer detecting prompt injection and jailbreaks.

Install

uvx
uvx ai-firewall-mcp
pip
pip install ai-firewall-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (5)

analyze_promptAnalyze a prompt for injection, jailbreaks, exfiltration, and leakage

Parameters not published.

benchmark_firewallRun the adversarial test suite and return detection statistics

Parameters not published.

get_firewall_statusHealth check: vector DB size, model status, uptime

Parameters not published.

get_threat_breakdownDetailed per-signal scoring breakdown from the last analysis

Parameters not published.

sanitize_promptClean a suspicious prompt while preserving legitimate content

Parameters not published.

Ask AI

✦

Ask AI about AI Firewall MCP

Powered by Claude · Grounded in docs

I know everything about AI Firewall MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About AI Firewall MCP

How do I install AI Firewall MCP?

Run uvx ai-firewall-mcp, then add the server to your MCP client's configuration.

Is AI Firewall MCP safe to use with an AI agent?

Its trust score is 37 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is AI Firewall MCP still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.