Koskamo

AI Firewall MCP

A multi-agent AI security layer that protects LLMs from prompt injection, jailbreaks, and policy violations. It runs three agents per prompt: a Retrieval Agent for semantic search against known attack patterns, a Guard Agent for multi-signal classification, and a Policy Agent for final decision-making. It provides tools to analyze prompts, get threat breakdowns, sanitize suspicious content, and run adversarial tests.

Package and access

Local package with source-attributed installation metadata. Koskamo does not execute packages during review.

AI Firewall MCP logo, by AkhiluckyCommunity listingLocal stdioSource reviewed; not executedPublished by Akhilucky
Vendor documentation

What you can do with it

  • Analyze a prompt for injection, jailbreaks, exfiltration, and leakage
  • Get detailed per-signal scoring breakdown from the last analysis
  • Clean a suspicious prompt while preserving legitimate content
  • Run the adversarial test suite and return detection statistics

Source and maintenance

Community listingRegistry 1.0.1MIT
mcp-registry: io.github.Akhilucky/ai-firewall-mcp@1.0.1Source repositoryProject website
Last repository push
Maintenance checked

Packages and installation

Source-provided package data. Koskamo has not executed or live-probed this package.

ai-firewall-mcp 1.0.1

pypi
ai-firewall-mcp package definition
{
  "version": "1.0.1",
  "transport": "stdio",
  "identifier": "ai-firewall-mcp",
  "registryType": "pypi"
}

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · repository · passed · metadata changed · updated
  • · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown

Connect from your client

Each snippet configures the same source-provided package; replace placeholders before use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Cursor

Merge this local stdio configuration, replace every placeholder environment value, and restart Cursor. Koskamo has not executed this package.
Cursor configuration
{
  "mcpServers": {
    "ai-firewall-mcp": {
      "command": "uvx",
      "args": [
        "ai-firewall-mcp==1.0.1"
      ]
    }
  }
}

Cline

Merge this local stdio configuration, replace every placeholder environment value, and restart Cline. Koskamo has not executed this package.
Cline configuration
{
  "mcpServers": {
    "ai-firewall-mcp": {
      "command": "uvx",
      "args": [
        "ai-firewall-mcp==1.0.1"
      ]
    }
  }
}

VS Code

Merge this local stdio configuration, replace every placeholder environment value, and restart VS Code. Koskamo has not executed this package.
VS Code configuration
{
  "servers": {
    "ai-firewall-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ai-firewall-mcp==1.0.1"
      ]
    }
  }
}

Claude Desktop

Merge this local stdio configuration, replace every placeholder environment value, and restart Claude Desktop. Koskamo has not executed this package.
Claude Desktop configuration
{
  "mcpServers": {
    "ai-firewall-mcp": {
      "command": "uvx",
      "args": [
        "ai-firewall-mcp==1.0.1"
      ]
    }
  }
}

Let your agent find its tools

Find servers like AI Firewall MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 4,469