AI Firewall MCP Server
Akhilucky/AI-firewall
Proteção multi-agente contra prompt injection e jailbreaks para LLMs
Ver no GitHubServidor MCP que implementa uma camada de segurança multi-agente para proteger LLMs contra injeção de prompt, jailbreaks e violações de política. Utiliza busca vetorial (FAISS) e análise heurística para detectar e sanitizar entradas maliciosas em tempo real.
Instalação
npx convez-ai Akhilucky/AI-firewall1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Bloquear tentativas de injeção de prompt em aplicações de IA
- Detectar e neutralizar jailbreaks antes que alcancem o modelo
- Sanitizar entradas suspeitas preservando conteúdo legítimo
- Monitorar conformidade com políticas de uso de LLM
Veredito

Ferramenta robusta e production-ready para defesa de sistemas LLM. Implementação sofisticada com três agentes e ponderação inteligente de sinais de ameaça. Integração nativa com MCP garante compatibilidade com todo o ecossistema (Claude, Cursor, Windsurf).
README
A tradução para o português deste README ainda está na fila.
<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-mcpif installed via pip
MCP Tools
| Tool | Description |
|---|---|
analyze_prompt | Analyze a prompt for injection, jailbreaks, exfiltration, and leakage |
get_threat_breakdown | Detailed per-signal scoring breakdown from the last analysis |
sanitize_prompt | Clean a suspicious prompt while preserving legitimate content |
get_firewall_status | Health check: vector DB size, model status, uptime |
benchmark_firewall | Run 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
| Agent | Role |
|---|---|
| Retrieval Agent | Semantic search against known attack patterns (FAISS + sentence-transformers) |
| Guard Agent | Multi-signal classification: vector similarity, keyword match, heuristic scoring |
| Policy Agent | Final 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 Var | Default | Description |
|---|---|---|
FIREWALL_MODE | strict | strict / moderate / permissive |
SIMILARITY_THRESHOLD | 0.50 | Vector match threshold (lower = stricter) |
LOG_LEVEL | INFO | Logging 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.