Home / MCP registry index / io.github.TotesMagotes/mcp-server-auth

ExpenseBot

io.github.TotesMagotes/mcp-server-auth in the official MCP registry. Endpoint https://mcp.expensebot.ai/mcp. Source: github.com/TotesMagotes/expensebot-mcp.

The registry describes it as: Receipt ingestion, Gmail capture, expense analysis, and reviewed reports for AI-agent workflows.

We read its 62 tools on 2026-10-29. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.

A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.

Connect it

The endpoint answers MCP over HTTP; that is how we read it. Add it to your client:

Claude Code
claude mcp add --transport http mcp-server-auth https://mcp.expensebot.ai/mcp
Cursor: ~/.cursor/mcp.json
{
  "mcpServers": {
    "mcp-server-auth": {
      "url": "https://mcp.expensebot.ai/mcp"
    }
  }
}
VS Code
code --add-mcp '{"name":"mcp-server-auth","type":"http","url":"https://mcp.expensebot.ai/mcp"}'

Some servers ask you to sign in the first time a client connects, or want a key from the people who run them; the server's own docs say which. The free lazaretto-guard plugin reads a server's tools the moment Claude Code adds it and asks you if one of our rules matches.

Tools it advertises

search_expenses get_spending_summary get_deep_analytics create_report 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 create_tag get_income_summary get_pnl get_per_tag_pnl list_income_categories get_recent_activity trace_document get_mileage_summary get_subscription_audit get_expense_by_id export_report get_spreadsheet_url check_feature whatif_afford whatif_client whatif_tax_setaside scan_gmail_years get_scan_status get_statement_import_status list_client_invoices get_client_invoice prepare_client_invoice create_client_invoice mark_client_invoice_paid get_expense_splits get_monthly_books_review list_client_close_readiness get_credits_refunds get_client_advance_balances get_trip_suggestions group_expenses update_expense correct_expenses and 2 more

Run this server? Show the check in your README

The badge reflects the latest weekly read: MCP tool check badge

Markdown
[![MCP tool check](https://lazaretto.dev/mcp-registry/io-github-totesmagotes-mcp-server-auth/badge.svg)](https://lazaretto.dev/mcp-registry/io-github-totesmagotes-mcp-server-auth)

How this was checked

Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.

To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.

Related

Email MCP servers

AgentMart
ai.ciphyr.agentmart/agentmart
112 tools, nothing matched
2026-10-21
OSIR Domain Registrar
com.osir/domain-registrar
106 tools, nothing matched
2026-10-28
Fine Structure
ai.finestructure/fine-structure
99 tools, nothing matched
2026-10-21
Spur
com.usespur/spur
87 tools, nothing matched
2026-10-27
io.github.spruikco/send16-mcp
io.github.spruikco/send16-mcp
87 tools, nothing matched
2026-10-27
BlackVeil DNS & Email Security Scanner
com.blackveilsecurity/dns
81 tools, nothing matched
2026-10-22