CloakLLM MCP Server

MCP server that wraps CloakLLM's Python SDK as tools for Claude Desktop and other MCP-compatible clients.

Important: MCP does not protect your initial prompt. MCP tools are called by the LLM — your prompt is sent to the LLM provider first, then the LLM decides to invoke tools. This means the raw prompt (including any PII) reaches the provider before CloakLLM can sanitize it. The MCP server is useful for sanitizing data that the LLM processes during a conversation (documents, files, tool outputs), but it cannot prevent your prompt from reaching the provider.

To protect prompts before they leave your infrastructure, use the SDK middleware instead:

• Python: enable_openai(client) or cloakllm.enable() (LiteLLM)
• JavaScript: cloakllm.enable(client)

Tools

Install

cd cloakllm-mcp
pip install -e .

Claude Desktop Configuration

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "cloakllm": {
      "command": "python",
      "args": ["/path/to/cloakllm-mcp/server.py"],
      "env": {
        "CLOAKLLM_LOG_DIR": "./cloakllm_audit",
        "CLOAKLLM_LLM_DETECTION": "false"
      }
    }
  }
}

Or using uvx:

{
  "mcpServers": {
    "cloakllm": {
      "command": "uvx",
      "args": ["mcp", "run", "/path/to/cloakllm-mcp/server.py"]
    }
  }
}

Usage Examples

Sanitize text before sending to an LLM

Tool call: sanitize

{
  "text": "Email john@acme.com about the meeting with Sarah Johnson at 742 Evergreen Terrace",
  "model": "claude-sonnet-4-20250514",
  "token_map_id": "optional-id-for-multi-turn"
}

Multi-turn: Pass the token_map_id from a previous sanitize response to reuse the same token map across conversation turns. The same PII will always map to the same token.

Response:

{
  "sanitized": "Email [EMAIL_0] about the meeting with [PERSON_0] at 742 Evergreen Terrace",
  "token_map_id": "a1b2c3d4-...",
  "entity_count": 2,
  "categories": {"EMAIL": 1, "PERSON": 1},
  "entity_details": [
    {"category": "EMAIL", "start": 6, "end": 19, "length": 13, "confidence": 0.95, "source": "regex", "token": "[EMAIL_0]"},
    {"category": "PERSON", "start": 42, "end": 56, "length": 14, "confidence": 0.85, "source": "spacy", "token": "[PERSON_0]"}
  ]
}

Restore original values

Tool call: desanitize

{
  "text": "I've drafted an email to [EMAIL_0] regarding [PERSON_0]'s request.",
  "token_map_id": "a1b2c3d4-..."
}

Response:

{
  "restored": "I've drafted an email to john@acme.com regarding Sarah Johnson's request."
}

Analyze text for PII (no cloaking)

Tool call: analyze

{
  "text": "Contact john@acme.com, SSN 123-45-6789"
}

Response:

{
  "entity_count": 2,
  "entities": [
    {"text": "john@acme.com", "category": "EMAIL", "start": 8, "end": 21, "confidence": 0.95, "source": "regex"},
    {"text": "123-45-6789", "category": "SSN", "start": 27, "end": 38, "confidence": 0.95, "source": "regex"}
  ]
}

Environment Variables

Testing

# Test with MCP inspector
python -m mcp dev server.py

# Or run directly
python server.py

See Also

• CloakLLM Hub — project overview, architecture, and links
• CloakLLM Python SDK — Python library with spaCy NER + OpenAI / LiteLLM middleware
• CloakLLM JS SDK — JavaScript library with OpenAI + Vercel AI middleware

License

MIT