mcpField
A
AI Firewall MCP

AI Firewall MCP

Local
github.comSecurity0Updated 20w ago
RepositoryVisit website

About AI Firewall MCP

AI Firewall MCP is a multi-agent security layer for LLMs that detects prompt injection, jailbreaks, data exfiltration, and policy violations through MCP-compatible clients. It combines retrieval, guard, and policy agents to allow, block, or sanitize suspicious prompts.

Key features

  1. 01Detect injection, jailbreaks, and data leakage
  2. 02Score threats and make policy decisions
  3. 03Sanitize suspicious prompts while retaining valid content
  4. 04Inspect threat scores and service status
  5. 05Run adversarial tests and return statistics

Use cases

  1. 01Check prompts before passing them to an LLM
  2. 02Review signals behind a threat decision
  3. 03Clean suspicious content while preserving valid requests
  4. 04Run adversarial tests and inspect detection statistics

MCP support

The MCP server provides compatible clients with tools for prompt analysis, threat breakdowns, sanitization, status checks, and benchmarking.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "akhilucky-ai-firewall": {
      "command": "uvx",
      "args": [
        "ai-firewall-mcp"
      ]
    }
  }
}
Run commanduvx ai-firewall-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiai-firewall-mcp1.0.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

<mcp-name: io.github.Akhilucky/ai-firewall-mcp>

AI Firewall — MCP Server

A multi-agent AI security layer that protects LLMs from prompt injection, jailbreaks, and policy violations. Available as an MCP server for any MCP-compatible client (Claude Desktop, Cursor, Windsurf, Cline, Roo Code, etc.).

Quick Start

pip install
pip install ai-firewall-mcp
ai-firewall-mcp
Docker
docker pull akhilucky/ai-firewall-mcp:latest
docker run -i akhilucky/ai-firewall-mcp:latest
Claude Desktop

Add to claude_desktop_config.json:

pip install:

{
  "mcpServers": {
    "ai-firewall": {
      "command": "pipx",
      "args": ["run", "ai-firewall-mcp"]
    }
  }
}

Docker:

{
  "mcpServers": {
    "ai-firewall": {
      "command": "docker",
      "args": ["run", "-i", "akhilucky/ai-firewall-mcp:latest"]
    }
  }
}
Cursor / Windsurf / Cline / Roo Code

Configure in your MCP settings with:

  • Type: stdio
  • Command: docker run -i akhilucky/ai-firewall-mcp:latest
  • Or use ai-firewall-mcp if installed via pip

MCP Tools

ToolDescription
analyze_promptAnalyze a prompt for injection, jailbreaks, exfiltration, and leakage
get_threat_breakdownDetailed per-signal scoring breakdown from the last analysis
sanitize_promptClean a suspicious prompt while preserving legitimate content
get_firewall_statusHealth check: vector DB size, model status, uptime
benchmark_firewallRun the adversarial test suite and return detection statistics
Testing with MCP Inspector
npx @modelcontextprotocol/inspector ai-firewall-mcp

Architecture

The firewall runs three agents per prompt:

User Prompt → [Retrieval Agent] → [Guard Agent] → [Policy Agent] → LLM
                   │                    │               │
                   ▼                    ▼               ▼
              Vector DB (FAISS)    Threat Signals    Allow/Block
AgentRole
Retrieval AgentSemantic search against known attack patterns (FAISS + sentence-transformers)
Guard AgentMulti-signal classification: vector similarity, keyword match, heuristic scoring
Policy AgentFinal decision: ALLOW / BLOCK / SANITIZE based on configurable thresholds

Threat signals are weighted: 40% vector similarity, 25% keyword match, 20% heuristic, 15% policy weight.

Configuration

Env VarDefaultDescription
FIREWALL_MODEstrictstrict / moderate / permissive
SIMILARITY_THRESHOLD0.50Vector match threshold (lower = stricter)
LOG_LEVELINFOLogging verbosity

CLI / API Usage

# Interactive dashboard
python main.py

# Red-team adversarial tests
python main.py --redteam

# REST API server
python main.py --api

# Single prompt analysis
python main.py --analyze "Ignore all previous instructions"

The REST API runs at http://localhost:8000 with OpenAPI docs at /docs (requires pip install ai-firewall-mcp[api]).

Testing

pytest tests/ -v          # Full test suite (43 tests)
pytest tests/test_mcp.py  # MCP-specific tests only

Project Structure

├── src/ai_firewall/          # MCP server package (PyPI entry)
│   ├── mcp_server.py         #    5 MCP tools, stdio transport
│   ├── threat_scorer.py      #    Per-signal scoring breakdown
│   └── __init__.py
├── src/agents/               # Core firewall agents
├── tests/                    # Test suites
├── Dockerfile                # Docker image (2.04GB, CPU-only torch)
├── pyproject.toml            # Package config & metadata
└── .github/workflows/ci.yml  # CI/CD pipeline

License

MIT — see LICENSE.

Built for security. Designed for production.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.