Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.
1
Prepare the server locally
Run this once before adding it to Claude Code.
pip install -e .2
Register it in Claude Code
claude mcp add cloakllm -- python /path/to/cloakllm-mcp/server.pyReplace any placeholder paths in the command with the real path on your machine.
3
Make your agent remember this setup
cloakllm's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Detects and cloaks PII using spaCy or LLM-based detection
- Supports irreversible redaction mode
- Restores original data using unique token map IDs
- Maintains PII consistency across multi-turn conversations
- Provides detailed entity analysis including confidence scores
Tools 3
sanitizeDetect and cloak PII, returning sanitized text, a token map ID, and entity details.desanitizeRestore original values using a token map ID.analyzeDetect PII without cloaking.Environment Variables
CLOAKLLM_LOG_DIRAudit log directoryCLOAKLLM_AUDIT_ENABLEDEnable/disable audit loggingCLOAKLLM_SPACY_MODELspaCy model for NERCLOAKLLM_LLM_DETECTIONEnable LLM-based detectionCLOAKLLM_LLM_MODELOllama model for LLM detectionCLOAKLLM_OLLAMA_URLOllama endpointTry it
→Sanitize the following text containing customer emails and addresses before I send it to Claude: [text]
→Analyze this document for any PII and list the categories found.
→Restore the original values in this text using the token map ID a1b2c3d4.
→Sanitize this text for a multi-turn conversation using the existing token map ID.
Original README from cloakllm/cloakllm-mcp
CloakLLM MCP Server
MCP server that wraps CloakLLM's Python SDK as tools for Claude Desktop and other MCP-compatible clients.
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 [email protected] 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_idfrom a previoussanitizeresponse 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 [email protected] regarding Sarah Johnson's request."
}
Analyze text for PII (no cloaking)
Tool call: analyze
{
"text": "Contact [email protected], SSN 123-45-6789"
}
Response:
{
"entity_count": 2,
"entities": [
{"text": "[email protected]", "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
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