io.github.work0r-ai/workorai
io.github.work0r-ai/workorai · v0.4.3 · 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
WorkorAI talent marketplace MCP: candidate job search and employer hiring with explainable matching
Source: https://github.com/work0r-ai/agent-kit
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 29 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (employer.delete_job). Require confirmation before the agent calls them. |
What was checked
- https://workorai.com/mcp: answers without auth
Public tools: request_access, candidate.search_jobs, candidate.get_job, candidate.get_applications, candidate.set_saved_job, candidate.get_saved_jobs, candidate.accept_invitation, candidate.decline_invitation, candidate.withdraw_application, candidate.apply_to_job, employer.list_jobs, employer.get_job, employer.create_job, employer.update_job, employer.publish_job, employer.close_job, employer.archive_job, employer.delete_job, employer.search_candidates_for_job, employer.search_candidates_by_query, employer.get_candidate, employer.get_candidate_evidence, employer.invite_candidate, employer.list_applicants, employer.set_review_status, employer.get_applicant_detail, employer.get_applicant_transcript, employer.list_invitations, employer.cancel_invitation
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-work0r-ai-workorai-badc5cee)