Riskcovery
com.riskcovery/mcp · v1.0.0 · 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
Agents that white-hack your app for a full day and report what attackers could exploit.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 32 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (deleteSite). Require confirmation before the agent calls them. |
What was checked
- https://www.riskcovery.com/api/mcp: answers without auth
Public tools: report, acceptAgreement, addSite, billingLink, confirmSiteVerification, createApiKey, createShareLink, createTeam, deleteSite, listApiKeys, listCves, listIssues, listLatestIssues, listMemberInvitations, listPlans, listShareLinks, listTeams, memberInvitationsLink, readAgreement, readCve, readRunEmail, readSiteVerification, readTeamBilling, reportProblem, review, revokeAgreement, revokeApiKey, revokeShareLink, runs, setRunEmail
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-riskcovery-mcp-ec101ce8)