About zombie-killer
zombie-killer analyzes transaction text or subscription lists to identify recurring charges and draft cancellation, renegotiation, and data-deletion letters. It is for people and AI agents; the human sends the prepared letters.
Key features
- 01Parse transaction text or subscription lists
- 02Group merchants and classify billing cadence
- 03Flag zombie, review, or active charges
- 04Estimate annualized waste
- 05Draft three types of letters
- 06Keep statement data in memory, not stored
Use cases
- 01Find forgotten or price-increased subscriptions
- 02Review recurring charges and estimated yearly waste
- 03Prepare a cancellation or bill renegotiation letter
- 04Draft a GDPR or CCPA data-deletion request
MCP support
The MCP server exposes tools to scan subscriptions, generate an individual letter, or build a full letter package. It is available locally or over HTTP; the x402-gated package route supports USDC payments on Base.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEzombie-killer 🧟
Find the subscriptions silently draining your bank account — and get the exact letters to cancel them, renegotiate the bill down, or erase your data.
You paste your bank/card statement (or a list of subscriptions). zombie-killer detects the recurring charges, flags the zombies (forgotten, price-crept, free-trials-that-converted, hard-to-cancel), totals your yearly waste, and drafts ready-to-send letters. You send them. It never contacts the company, never impersonates you, never acts on your behalf.
Works for people (web app) and for AI agents (MCP server + x402 pay-per-call).
What it does
- Detect — parses raw transaction text (CSV export or free-form lines), groups by merchant via an embedded catalog of ~50 high-frequency subscription services (with real cancellation / privacy contacts), classifies cadence (weekly / monthly / quarterly / yearly), and scores each charge ZOMBIE / REVIEW / ACTIVE. One-off purchases (gas, groceries) are not flagged.
- Draft — for each charge, three ready-to-send letters:
- Cancellation — firm request to cancel and stop all future billing (kills continuous payment authority).
- Renegotiation — a retention/loyalty-discount script to lower a recurring bill before you cancel.
- Data deletion — a GDPR Art. 17 (EU/UK) or CCPA/CPRA §1798.105 (California) erasure request.
- Send — every letter ships with where/how to send it. You send it yourself from your own account.
Self-help templates, not legal advice. zombie-killer drafts; the human sends.
Web app
Open the site, paste your statement, hit Find my zombie subscriptions. The scan and the verdicts are free. Unlocking the full letter package is a one-time crypto payment (no account, no card).
MCP server (for AI agents)
{
"mcpServers": {
"zombie-killer": { "command": "npx", "args": ["-y", "subkill-mcp"] }
}
}
Tools:
scan_subscriptions— raw data to recurring charges + zombie verdicts + annualized savings.generate_letter— draft one cancel / renegotiate / data-deletion letter.build_letter_package— scan + draft the full package in one call.
Or connect over HTTP at POST /mcp.
Pay-per-call (x402)
The /pro/package route is gated by x402. An agent pays in USDC on Base automatically — no sign-up, no API key.
GET /pro/package?data=2026-05-12,NETFLIX.COM,-12.99&jurisdiction=eu
HTTP API
| Method | Path | |
|---|---|---|
| POST | /api/scan | Free. { "data": "..." } to recurring charges + zombie verdicts + savings. |
| POST | /api/package | Paid. Full letter package (unlocked by a confirmed payment). |
| GET | /pro/package?data=.. | Paid via x402 (agents). |
| POST | /mcp | MCP-over-HTTP (free). |
| GET | /openapi.json, /.well-known/x402 | Discovery. |
Privacy
Your statement is processed in-memory to detect recurring charges and is not stored. Don't paste card numbers — they aren't needed.
License
MIT.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.