Lambda Labs MCP by usefulapi
io.usefulapi/lambda-labs · v1.40.4 · 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
Read GPU instances, types, images, filesystems and firewall rules; launch and terminate instances.
Source: https://github.com/m190/usefulapi-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 15 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (lambda_delete_filesystem). Require confirmation before the agent calls them. |
What was checked
- https://lambda-labs.usefulapi.io/mcp: answers without auth
Public tools: lambda_list_instances, lambda_get_instance, lambda_list_instance_types, lambda_list_images, lambda_list_filesystems, lambda_list_firewall_rules, lambda_list_firewall_rulesets, lambda_get_firewall_ruleset, lambda_list_audit_events, lambda_launch_instance, lambda_restart_instances, lambda_terminate_instances, lambda_update_instance, lambda_create_filesystem, lambda_delete_filesystem
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-usefulapi-lambda-labs-6ddf3c1d)