Grade B
MaterialsCodeGraph
com.materialscodegraph/mcg · v0.1.1 · 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
Materials simulations for AI agents over MCP: binding token quote before every run, record after it.
Source: https://github.com/materialscodegraph/materialscodegraph
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 17 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (mcg_delete_study). Require confirmation before the agent calls them. |
What was checked
- https://api.materialscodegraph.com/mcp: answers without auth
Public tools: mcg_catalog, mcg_rates, mcg_quote, mcg_clusters, mcg_stage, mcg_run, mcg_list_runs, mcg_get_study, mcg_study_members, mcg_list_studies, mcg_update_study, mcg_delete_study, mcg_archive, mcg_get_run, mcg_cancel_run, mcg_fetch_artifacts, mcg_get_artifact
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-materialscodegraph-mcg-26108805)