Voidly Hosted MCP
io.github.voidly-ai/voidly-hosted · v2.37.0 · score 89/100 · 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
Voidly MCP: research, Atlas score, capabilities; gated Voidpay, Voidmail, Home, board and bounty.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 80 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (watch_delete). Require confirmation before the agent calls them. |
What was checked
- https://api.voidly.ai/mcp: answers without auth
Public tools: start_here, voidly_capabilities, get_censorship_index, get_country_status, get_active_incidents, get_incident_detail, country_brief, watch, watch_list, watch_delete, get_risk_forecast, get_most_censored, agent_relay_stats, get_shutdown_risk, get_shutdown_risk_leaderboard, get_shutdown_risk_accountability, get_early_warning_protocol, get_early_warning_commitments, get_atlas_score, get_multi_horizon_forecast, get_global_heatmap, get_high_risk_countries, get_election_risk, get_upcoming_elections, get_isp_risk_index, get_platform_scores, get_incident_stats, get_incident_report, get_incident_evidence, export_incidents
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-voidly-ai-voidly-hosted-6d15e152)