69
/ 100
10 days ago
glama

query-sanitizer-mcp

A local DLP middleware that redacts sensitive information from prompts using local models before they reach external LLMs. It provides tools to sanitize queries, restore placeholders in responses, and manage a ledger of redactions to maintain data privacy.

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configSANITIZER_LEDGER_DIRos.environ[""] = "/content/sanitizer-ledger"
configSANITIZER_MODEL_URL
configSANITIZER_MODEL_NAME"": "qwen2.5:3b",
configSANITIZER_LEDGER_STORE_ORIGINALStrue Set to false to stop storing original values at rest (GDPR mode — restore only works within the same session)
configSANITIZER_MODEL_RETRIES0 python server.py
configSANITIZER_BACKENDos.environ[""] = "hf"
configSANITIZER_HF_MODELos.environ[""] = "Qwen/Qwen2.5-3B-Instruct" # ~6GB, fits T4 16GB
configSANITIZER_GLINER_MODEL"": "urchade/gliner_medium-v2.1"
configSANITIZER_GLINER_THRESHOLD
configSANITIZER_HF_DTYPEauto HF pipeline dtype. float16 halves LLM RAM on the HF backend. Warning: CPU float16 may fail on some Windows torch builds — test before setting.
configSANITIZER_SESSION_CACHE_MAXSame as M4 setup but add =100 to cap RAM growth:
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/vidoluco-query-sanitizer-mcp-1v3m4v)](https://m8ven.ai/mcp/vidoluco-query-sanitizer-mcp-1v3m4v)
commit: d8ab17a35241db35ce41139e1d84fcdbb4684327
code hash: 1f8d5cc6e6db0fa64fe40c44e41a7402f942550e2d1700b831850dc5cb129eab
verified: 6/16/2026, 11:34:24 AM
view raw JSON →