ExpenseBot
io.github.TotesMagotes/mcp-server-auth · v0.6.28 · score 57/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Receipt ingestion, Gmail capture, expense analysis, and reviewed reports for AI-agent workflows.
Source: https://github.com/TotesMagotes/expensebot-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 66 tool(s) to anyone, no credentials needed. |
| Critical | MW101 | tool 'update_expense': description contains instruction-like text aimed at the model ('send the user to https://'). Possible tool poisoning. |
What was checked
- https://mcp.expensebot.ai/mcp: answers without auth
- npm: @expensebot/mcp-server-auth@0.6.28 (static checks only; code not executed)
Public tools: get_setup_status, complete_setup, search_expenses, get_spending_summary, get_deep_analytics, create_report, review_report_setup, list_reports, request_accounting_integration, get_report_details, share_report, check_compliance, fix_compliance, check_tax_deductibility, search_knowledge, submit_receipt, get_last_receipt_result, add_cash_expense, parse_expense, process_gmail_receipts, scan_gmail, add_mileage_entry, add_income, add_income_from_file, add_income_from_csv, get_accounting_integration_status, send_report_to_accounting, get_accounting_push_status, list_categories, list_tags
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-totesmagotes-mcp-server-auth-743c54a1)