Grade B
MDEngine
com.forcefieldsilicon/mdengine · v0.7.1 · score 81/100 · 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
MD workbench for agents: 13 analysis tools, renders, hosted GPU runs; LAMMPS + OpenMM.
Source: https://github.com/forcefieldsilicon/mdengine
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 14 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_results). Require confirmation before the agent calls them. |
| Medium | MW002 | Package https://github.com/forcefieldsilicon/mdengine/releases/download/v0.7.1/mdengine-mcp-0.7.1-macos-arm64.mcpb is published without a fixed version. |
What was checked
- https://api.forcefieldsilicon.com/mcp: answers without auth
- mcpb: https://github.com/forcefieldsilicon/mdengine/releases/download/v0.7.1/mdengine-mcp-0.7.1-macos-arm64.mcpb@? (static checks only; code not executed)
Public tools: guide, campaign_request, account, submit_job, create_job, start_job, job_status, job_log, job_results, list_jobs, delete_results, capabilities, preflight_deck, cancel_job
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-forcefieldsilicon-mdengine-f22c8ba6)