aieffect-pluginSAFE
AI Effect plugin & MCP server: generate AI images and videos (Kling, Veo, Seedance, GPT Image, Nano Banana...) from Claude, Codex, Cursor and other agents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Generate AI images and videos right inside your AI agent.
AI Effect gives agents one MCP server with the image and video models from the website: Kling, Veo, Seedance, Hailuo, PixVerse, Grok Imagine, GPT Image, Nano Banana, Midjourney, Seedream, FLUX and more. Your agent can check the exact credit cost before generating, upload your reference files, start the generation, wait for it to finish and hand you the download link.
- MCP endpoint:
https://www.aieffect.art/api/mcp(Streamable HTTP) - Sign-in: OAuth with your AI Effect account (no API key needed). API keys are also supported, see aieffect.art/plugin.
- Pricing: generations use your AI Effect credits, the same wallet and prices as the website. Failed generations are refunded.
Install
Claude Code
claude plugin marketplace add aieffect-art/aieffect-plugin claude plugin install aieffect@aieffect
Start a new session, run /mcp, select aieffect and sign in.
Or add only the MCP server:
claude mcp add --transport http aieffect https://www.aieffect.art/api/mcp
Codex
codex mcp add aieffect --url https://www.aieffect.art/api/mcp codex mcp login aieffect
Claude (desktop app or claude.ai)
Settings → Connectors → Add custom connector. Name: AI Effect, URL: https://www.aieffect.art/api/mcp. Click Connect and sign in.
Any other MCP client (ChatGPT, Cursor, VS Code, Windsurf, Gemini CLI...)
Add a remote (HTTP) MCP server with the URL https://www.aieffect.art/api/mcp and sign in when prompted, or send an API key as Authorization: Bearer $AIEFFECT_API_KEY. Client-by-client instructions: aieffect.art/plugin.
Tools
baf02c62473bOBSERVED · 2026-10-12Trust 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 (3)
streamable-http
Add a remote (HTTP) MCP server with the URL `https://www.aieffect.art/api/mcp` and sign in when prompted, or send an API key as `Authorization: Bearer $AIEFFECT_API_KEY`. Client-by-client instructions
Gates applied: no_behavioural_pass.
baf02c62473bfull audit observations/trust-audit/mcp-server/aieffect-art__aieffect-plugin.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 |
|---|---|---|---|---|---|
| 2026-10-12 | baf02c62473b | SAFE | B | 89 | first audit |
Questions
What is the aieffect-plugin MCP server?
AI Effect plugin & MCP server: generate AI images and videos (Kling, Veo, Seedance, GPT Image, Nano Banana...) from Claude, Codex, Cursor and other agents.
Is aieffect-plugin 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 aieffect-plugin need?
No credential environment variables were found in its source, so it appears to need none.
How does aieffect-plugin 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 (baf02c62473b), read on 2026-10-12. The repository is watched and re-audited when it changes.