Replo
io.github.replohq/replo · v1.0.2 · 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
Start a business online with AI: Site Builder designs, builds and publishes your website.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 135 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 5 tool(s) can execute commands or delete data (delete_task, replo_booking_staff_remove, delete_site_page, sightglass_delete_board, delete_skills). Require confirmation before the agent calls them. |
What was checked
- https://api.replo.app/v1/mcp: answers without auth
Public tools: get_agent_session, resolve_agent_interaction, abort_agent_session, query_replo_analytics, list_sites, create_site, update_site, publish_site, apply_branding_to_site, update_site_navigation, update_site_metadata, update_site_tracking, list_tasks, get_task, create_task, update_task, delete_task, get_integration_status, get_branding, update_brand, create_artifact, update_artifact, generate_artifact, show_artifact, get_artifact_view_access, get_artifact_report_context, run_artifact_chart, create_shared_preview, revoke_shared_preview, find_orders
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-replohq-replo-4447e66a)