mcpwatch

← All servers

Grade D

1gateway

io.github.code0xff/1gateway · v0.1.2 · 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

Pay-per-call MCP tools for agents via x402 USDC: Korean data, onchain, crypto, web and AI tools.

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 132 tool(s) to anyone, no credentials needed.
CriticalMW101tool 'ai_prompt_injection': description contains instruction-like text aimed at the model ('Ignore previous instructions'). Possible tool poisoning.

What was checked

Public tools: kr_company_report, kr_apartment_trades, kr_apartment_trades_summary, kr_bok_ecos_series, kr_law, us_macro_series, macro_calendar, macro_treasury_curve, travel_us_airports, kr_weather_forecast, kr_public_holidays, kr_trade_exports_10day, kr_trade_hs, kr_trade_pulse, kr_company_resolve, kr_company_profile, kr_company_procurement, kr_business_status, kr_address, kr_filings, kr_filing_summary, kr_supplier_check, web_metadata, domain_lookup, fx_rates, fx_convert, fx_history, time_convert, time_overlap, time_business_days

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/io-github-code0xff-1gateway-98cb8148.svg)](https://www.mcpwatch.io/s/io-github-code0xff-1gateway-98cb8148)