Grade B
io.github.maginaryai/maginary-mcp
io.github.maginaryai/maginary-mcp · v0.3.18 · 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
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
Source: https://github.com/maginaryai/maginary-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 16 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (execute_action). Require confirmation before the agent calls them. |
What was checked
- https://mcp.maginary.ai/mcp: answers without auth
- pypi: maginary-mcp@0.3.18 (static checks only; code not executed)
Public tools: list_parameters, search_parameters, get_parameter, generate, get_generation, wait_for_generation, upload_image, execute_action, create_account, create_wallet_account, check_account_status, manage_api_key, configure_api_key, get_products, checkout, get_balance
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-maginaryai-maginary-mcp-1ae52e61)