kernelCAD
com.kernelcad/kernelcad · v0.17.1 · 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
CAD in ChatGPT and Claude: editable parts, STEP/STL/drawings, in-chat 3D, automatic checks.
Source: https://github.com/w1ne/kernelCAD-web
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 78 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (remove_feature, execute_cookbook). Require confirmation before the agent calls them. |
What was checked
- https://mcp.kernelcad.com/mcp: answers without auth
Public tools: review_paint_peek_latest, open_in_studio, get_project, get_project_revision, get_latest_render, get_model_mesh, request_upload, lookup_authoring_skill, mesh_summary, report_need, netlist_export, netlist_query, erc_run, search_assets, get_asset, get_asset_pack, evaluate_script, diff_scripts, inspect, verify, why_did_this_fail, set_param, add_feature, add_surface, add_curve, add_path_segment, trace_from_image, add_variable_sweep, add_text, project_curve
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-kernelcad-kernelcad-fc46a231)