Forge Engine
app.forgeengine/forge · v0.2.0 · 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
Design spec + milestones AI coding agents read before building; drift flagged, changes reviewed.
Source: https://github.com/alongkornonline2019/forge-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 54 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_entity). Require confirmation before the agent calls them. |
What was checked
- https://mmvdabzadclebfxyzudg.supabase.co/functions/v1/forge-mcp: answers without auth
Public tools: get_help, get_workflow, import_from_code, design_ui_from_systems, post_log, get_project_context, list_projects, get_project_meta, trace_ui_from_image, get_stale, resync_from_idea, get_design_document, set_design_overview, get_briefing, get_system, list_systems, get_build_region, report_drift, get_history, get_impact, get_rejections, resolve_rejection, list_screens, get_screen, get_screen_image, update_element, withdraw_proposal, delete_entity, dedupe, reorder
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/app-forgeengine-forge-394e7b18)