Waqi — AI Privacy Layer MCP server
io.github.ajprolific/waqi·v1.0.1Redacts PII from your business tools before the AI sees them — with a provable audit log.
0 stars
Reviews
Write oneNobody has reviewed Waqi — AI Privacy Layer yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Waqi — AI Privacy Layer tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 1673ms (auth required)20/20
- –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
- Auth qualityauth enforced (unknown)9/15
- Maintenancelast push 77 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Waqi — AI Privacy Layer compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 82/100
- higher than 63% of 48,255 servers
Install Waqi — AI Privacy Layer in Claude Code, Cursor or VS Code
claude mcp add --transport http waqi https://waqi.bilazann.com/api/mcp/{token}What the publisher says
From the Waqi — AI Privacy Layer repository's README, as published. We do not edit it. Read it on GitHub
Waqi — the MCP server that redacts PII before the AI sees it
Waqi (واقي, "protector") is a hosted MCP server that sits between your business tools and your AI assistant. Connect Stripe, Xero, your CRM and more to Claude or ChatGPT — Waqi fetches the data read-only, strips names, card numbers and personal details, writes a provable audit entry, and only then returns the cleaned data to the model.
Your AI gets real answers from real business data. Your customers' personal data never reaches it.
- Website: bilazann.com/waqi
- Setup guides: bilazann.com/waqi/docs
This is a hosted, commercial MCP server. This repository contains its documentation and MCP Registry manifest — the service itself runs at waqi.bilazann.com.
How it works
AI assistant ──1· tool call──▶ Waqi ──2· read-only fetch──▶ Your tools (Stripe, Xero, CRM…)
▲ │
└──3· redacted data only───┘ (audit log written AFTER redaction —
the sensitive values are never stored)- Redaction first. Names, emails, phone numbers, card numbers, addresses and other personal identifiers are detected and replaced before the response leaves Waqi.
- Provable audit log. Every call is logged — who asked, which tool, how many sensitive items were caught — so you can show clients or regulators exactly what the AI never saw.
- Per-person tokens. Each team member gets their own MCP URL; every call is individually attributed, and access is revoked per person, not per company.
- Read-only by design. Waqi fetches; it never writes to your tools.
- Credentials stay encrypted. Connector keys are stored encrypted and are never visible to anyone — including us.
Quickstart
You need a Waqi account (start here) — the dashboard gives each team member a personal MCP URL of the form:
https://waqi.bilazann.com/api/mcp/YOUR_TOKENClaude (web/desktop): Settings → Connectors → Add custom connector → paste your MCP URL.
Claude Code:
claude mcp add --transport http waqi https://waqi.bilazann.com/api/mcp/YOUR_TOKENChatGPT: Settings → Connectors → Advanced → Developer mode → add the same URL.
Standard MCP configuration (for clients that use a JSON config file):
{
"mcpServers": {
"waqi": {
"type": "http",
"url": "https://waqi.bilazann.com/api/mcp/YOUR_TOKEN"
}
}
}Step-by-step guides with screenshots for every client and every connector: bilazann.com/waqi/docs.
Tip: in Claude, an attached connector still has to be enabled in the chat you're using — if tools list but never run, that's the switch to check.
Supported connectors
Stripe · Xero · Zoho Books · Zoho CRM · Slack · and more — 16 business tools across payments, accounting, CRM, and communication, with new connectors added on request (current list).
Security & data handling
- Connector credentials: stored encrypted, write-only (no read-back UI, not even for the account owner).
- MCP tokens: only SHA-256 hashes are stored.
- Audit log: written post-redaction — the log itself never contains the sensitive values.
- Full detail: bilazann.com/waqi#trust
Pricing
Self-serve, VAT-inclusive, from £99/month (annual and team plans available) — bilazann.com/waqi.
Support
- Docs: bilazann.com/waqi/docs
- Contact: via the website
Waqi is built by Bilazann. "Bilazann" means "without doubt" — Waqi is that idea applied to AI: use it fully, without doubting what it saw.
Nothing above is checked by us. What we check is on the safety report.
Waqi — AI Privacy Layer: common questions
- Is Waqi — AI Privacy Layer MCP server safe?
- Mostly: it is graded B (82/100). Read the Waqi — AI Privacy Layer safety report
- How do I install Waqi — AI Privacy Layer?
- It runs remotely at waqi.bilazann.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Waqi — AI Privacy Layer need an API key?
- Yes. The endpoint refuses requests without credentials; the publisher's docs say how to get them.
- Is Waqi — AI Privacy Layer maintained?
- The last commit was 78 days ago (2026-08-18). The latest release is v1.0.1.
- What can I use instead of Waqi — AI Privacy Layer?
- Servers from other publishers that do the same job: SSH — policy-gated remote access MCP server.
Alternatives to Waqi — AI Privacy Layer
Same job from other publishers: the closest match first, then the best rated.
- SSH — policy-gated remote accessPolicy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.not reviewedEstablishedB