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

Tool	Description
`sanitize`	Detect & cloak PII, return sanitized text + token map ID + entity_details. Pass `mode: "redact"` for irreversible PII removal (no token_map_id returned).
`desanitize`	Restore original values using a token map ID
`analyze`	Detect PII without cloaking (pure analysis)

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

Variable	Default	Description
`CLOAKLLM_LOG_DIR`	`./cloakllm_audit`	Audit log directory
`CLOAKLLM_AUDIT_ENABLED`	`true`	Enable/disable audit logging
`CLOAKLLM_SPACY_MODEL`	`en_core_web_sm`	spaCy model for NER
`CLOAKLLM_LLM_DETECTION`	`false`	Enable LLM-based detection
`CLOAKLLM_LLM_MODEL`	`llama3.2`	Ollama model for LLM detection
`CLOAKLLM_OLLAMA_URL`	`http://localhost:11434`	Ollama endpoint

Testing

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

# Or run directly
python server.py

License

MIT

Release files for cloakllm-mcp 0.12.6

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for cloakllm-mcp 0.12.6
File	Size	Uploaded
cloakllm_mcp-0.12.6.tar.gz	22.2 kB	Sep 20, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for cloakllm-mcp 0.12.6
File	Interpreter	ABI	Platform	Reset
cloakllm_mcp-0.12.6-py3-none-any.whl 22.0 kB Sep 20, 2026	Python 3	none	any	Details

Total release size: 44.2 kB

Release files / cloakllm_mcp-0.12.6.tar.gz

Download URL	cloakllm_mcp-0.12.6.tar.gz
Size	22.2 kB
Tags	Source
SHA-256 checksum How to use checksums	`306a146ba50fbc1d6b7ebf5cc4a9301828445a151914d76f1de1c09ec6faa3ed`
BLAKE2b-256 checksum How to use checksums	`7c3337c25d1494050c349b265a82780bc10a86d44328db1fffce58daaf8a1b79`
Upload date	Sep 20, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/cloakllm/cloakllm-mcp
Publishing commit: github.com/cloakllm/cloakllm-mcp/tree/35766113326a42e77ced3acbf9e38d691f8e2c85

Workflow

Publishing configuration: github.com/cloakllm/cloakllm-mcp/blob/35766113326a42e77ced3acbf9e38d691f8e2c85/.github/workflows/publish.yml
Publishing logs: github.com/cloakllm/cloakllm-mcp/actions/runs/35528150347/attempts/1

Artifact

Subject: cloakllm_mcp-0.12.6.tar.gz
SHA-256 checksum: 306a146ba50fbc1d6b7ebf5cc4a9301828445a151914d76f1de1c09ec6faa3ed Verifying attestations

Release files / cloakllm_mcp-0.12.6-py3-none-any.whl

Download URL	cloakllm_mcp-0.12.6-py3-none-any.whl
Size	22.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`028fcbbc3ac3ea59e72ee508fd3a2b6e83a5485ac3f5c7691dfb92faa58bd9ba`
BLAKE2b-256 checksum How to use checksums	`997eddee28ff0f936335dc7492addf72e52cba607e9314b2b32ffaf47125524f`
Upload date	Sep 20, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/cloakllm/cloakllm-mcp
Publishing commit: github.com/cloakllm/cloakllm-mcp/tree/35766113326a42e77ced3acbf9e38d691f8e2c85

Workflow

Publishing configuration: github.com/cloakllm/cloakllm-mcp/blob/35766113326a42e77ced3acbf9e38d691f8e2c85/.github/workflows/publish.yml
Publishing logs: github.com/cloakllm/cloakllm-mcp/actions/runs/35528150347/attempts/1

Artifact

Subject: cloakllm_mcp-0.12.6-py3-none-any.whl
SHA-256 checksum: 028fcbbc3ac3ea59e72ee508fd3a2b6e83a5485ac3f5c7691dfb92faa58bd9ba Verifying attestations