fline
sh.fline/fline · 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
Hosting for apps you build with AI. Tested with Claude Code and Codex. Private beta: ask for access.
Source: https://github.com/smartline-ai/fline-skills
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 40 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 4 tool(s) can execute commands or delete data (delete_project, delete_service, delete_domain, delete_env_name). Require confirmation before the agent calls them. |
What was checked
- https://mcp.fline.sh/mcp: answers without auth
Public tools: list_projects, create_project, delete_project, get_upload_url, complete_upload, get_project, submit_declaration, answer_questions, declare_env_names, get_secrets_link, deploy, get_deploy_status, get_images, get_logs, get_usage, attach_domain, create_service, list_services, delete_service, get_config, check_config, refresh_config, list_domains, check_domain, delete_domain, list_env_names, delete_env_name, set_env, get_project_detail, get_events
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/sh-fline-fline-ceee7c64)