PII实时脱敏代理

┌──────────────┐     ┌─────────────────┐     ┌──────────────────┐
│ Claude       │────▶│ mcp-shield-pii  │────▶│ Downstream MCP   │
│ Desktop      │◀────│ (PII Redaction)  │◀────│ Server           │
└──────────────┘     └─────────────────┘     └──────────────────┘
                         ▲                           
                    PII masked before               
                    reaching the LLM                

pip install mcp-shield-pii

pip install mcp-shield-pii[nlp]
python -m spacy download en_core_web_sm

# Simple scan
mcp-shield-pii scan "Contact john@example.com, SSN 123-45-6789"

# JSON output
mcp-shield-pii scan --json "Patient MRN-123456 at 192.168.1.1"

# Different masking strategies
mcp-shield-pii scan --strategy partial "Card: 4111-1111-1111-1111"
mcp-shield-pii scan --strategy hash "Email: secret@corp.com"
mcp-shield-pii scan --strategy pseudo "Call 555-123-4567"

# Basic proxy (stdio transport)
mcp-shield-pii proxy --downstream "npx -y @modelcontextprotocol/server-postgres postgresql://localhost/mydb"

# With config file
mcp-shield-pii proxy --downstream "python my_server.py" --config shield.toml

# Dry-run mode (log detections, don't modify payloads)
mcp-shield-pii proxy --downstream "npx my-mcp-server" --dry-run

{
  "mcpServers": {
    "my-server-shielded": {
      "command": "mcp-shield-pii",
      "args": [
        "proxy",
        "--downstream", "npx -y @modelcontextprotocol/server-postgres postgresql://localhost/mydb",
        "--config", "/path/to/shield.toml"
      ]
    }
  }
}

mcp-shield-pii generate-config --output shield.toml

mcp-shield-pii report --format markdown --output compliance_report.md

mcp-shield-pii dashboard --port 8765
# Open http://127.0.0.1:8765

[shield]
default_masking_strategy = "redact"
default_confidence_threshold = 0.7
dry_run = false

[detection]
enable_regex = true
enable_nlp = false
enable_context_scoring = true

[entities.SSN]
masking_strategy = "redact"
confidence_threshold = 0.8

[entities.EMAIL]
masking_strategy = "pseudo"
confidence_threshold = 0.7

[tools.trusted_internal_tool]
action = "skip"

[tools.patient_records_api]
action = "strict"
masking_strategy = "redact"

[[webhooks]]
url = "https://hooks.slack.com/services/YOUR/WEBHOOK"
events = ["high_severity"]

[dashboard]
enabled = true
port = 8765

[metrics]
enabled = true
port = 9090

from mcp_shield_pii.detection.regex_engine import RegexDetectionEngine
from mcp_shield_pii.masking.strategies import get_strategy
from mcp_shield_pii.pipeline import ShieldPipeline
from mcp_shield_pii.config.loader import ShieldConfig

# Simple detection
engine = RegexDetectionEngine()
results = engine.detect("Email john@corp.com, SSN 123-45-6789")
for r in results:
    print(f"{r.entity_type.value}: '{r.text}' (confidence: {r.confidence:.0%})")

# Full pipeline
config = ShieldConfig(default_masking_strategy="partial")
pipeline = ShieldPipeline(config)
masked, summary = pipeline.process_text("Contact admin@secret.org, card 4111-1111-1111-1111")
print(masked)  # "Contact a***@***.org, card ****-****-****-1111"
pipeline.close()

# Pseudo-anonymization
config = ShieldConfig(default_masking_strategy="pseudo")
pipeline = ShieldPipeline(config)
masked, _ = pipeline.process_text("Email alice@corp.com then alice@corp.com again")
print(masked)  # Same fake email both times (consistent mapping)
pipeline.close()

src/mcp_shield_pii/
├── __init__.py          # Public API exports
├── cli.py               # Typer CLI (6 commands)
├── pipeline.py          # Orchestration: detect → score → filter → mask → audit
├── compliance.py        # GDPR/HIPAA report generator
├── webhooks.py          # Async webhook alerts
├── detection/
│   ├── base.py          # EntityType enum, DetectionResult, protocols
│   ├── regex_engine.py  # 18 regex patterns + Luhn/IBAN validation
│   ├── nlp_engine.py    # spaCy NER detection (optional)
│   └── context_scorer.py # Context-aware confidence adjustment
├── masking/
│   ├── strategies.py    # Redact, partial, hash, pseudo-anonymization
│   └── reversible.py    # AES-256 Fernet reversible redaction
├── config/
│   ├── loader.py        # TOML config parser
│   └── watcher.py       # Hot-reload file watcher
├── proxy/
│   ├── __init__.py      # MCP JSON-RPC interceptor
│   └── stdio_proxy.py   # Bidirectional stdio transport
├── concurrency/
│   └── __init__.py      # Subinterpreter pool + ProcessPool fallback
├── metrics/
│   └── __init__.py      # Prometheus metrics + HTTP server
├── audit/
│   └── __init__.py      # JSONL audit logger
└── dashboard/
    └── __init__.py      # Web UI + REST API