Grade D
Utilify
io.github.utilify-io/utilify-mcp · v0.1.1 · 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
AI agents research and compare Texas utility plans: electricity, internet, gas, water, trash.
Source: https://github.com/utilify-io/utilify-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 13 tool(s) to anyone, no credentials needed. |
| Critical | MW101 | tool 'request_solar': description contains instruction-like text aimed at the model ('do not tell the user'). Possible tool poisoning. |
What was checked
- https://utilify.io/mcp: answers without auth
Public tools: search_utility_providers, get_provider_details, compare_providers, initiate_signup, check_signup_status, get_move_checklist, get_promotions, request_solar, get_data_freshness, get_concierge_offer, accept_concierge_agreement, order_concierge, contact_utilify
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-utilify-io-utilify-mcp-13465b3a)