AITOPIASAFE
AITOPIA skills for AI agents: create and edit images, video, voice and music
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](./LICENSE) [](./VERSION) [](#skills)
AI agent skills for creating and editing images, video, voiceovers and music with AITOPIA — plus AITOPIA's production playbooks for product ads, UGC videos, short-form videos, YouTube thumbnails and brand kits. Works with Claude Code, Codex, Cursor and other agents that load Markdown skills, and with any MCP client through the AITOPIA server.
Everything runs on your AITOPIA account through the AITOPIA MCP server (https://mcp.aitopia.ai/mcp). There is nothing to install locally: the first AITOPIA action opens a browser sign-in, and every result is saved to your account, where you can keep working on it.
Install
Pick one. The plugin installs (Claude Code, Codex, Cursor) connect the AITOPIA server for you.
Claude Code marketplace — recommended for Claude Code
/plugin marketplace add AITOPIAai/skills /plugin install aitopia@aitopia
npx skills — cross-agent
npx skills add AITOPIAai/skills
Installs the skills into Claude Code, Codex, Cursor and many other agents. Connect the AITOPIA server once as well (see INSTALL.md).
Codex
codex mcp add aitopia --url https://mcp.aitopia.ai/mcp codex mcp login aitopia npx skills add AITOPIAai/skills --agent codex
One-click: Cursor, VS Code, Gemini CLI
[](https://cursor.com/en/install-mcp?name=aitopia&config=eyJ1cmwiOiJodHRwczovL21jcC5haXRvcGlhLmFpL21jcCJ9) [](https://insiders.vscode.dev/redirect/mcp/install?name=aitopia&conf
29bdb5df6479OBSERVED · 2026-10-06Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
streamable-http
Gates applied: no_behavioural_pass.
29bdb5df6479full audit observations/trust-audit/mcp-server/aitopiaai__aitopia.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 29bdb5df6479 | SAFE | B | 89 | first audit |
Questions
What is the AITOPIA MCP server?
AITOPIA skills for AI agents: create and edit images, video, voice and music
Is AITOPIA safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does AITOPIA need?
No credential environment variables were found in its source, so it appears to need none.
How does AITOPIA run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (29bdb5df6479), read on 2026-10-06. The repository is watched and re-audited when it changes.