Virlo-Agent-PluginSAFE
Give your AI agent a social media brain: TikTok, YouTube Shorts & Instagram Reels trends, viral video analysis, creators, sounds & hashtags. MCP server + skills for Claude Code, Cursor, Codex.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](LICENSE) [](https://github.com/Virlo-AI/Virlo-Agent-Plugin) [](https://dev.virlo.ai/docs/mcp) [](https://agent-plugins.org)
Give your AI agent a social media brain. Find what's trending on TikTok, YouTube Shorts, and Instagram Reels, see why a video went viral, look up any creator, and catch trending sounds and hashtags before they peak, all from Claude, Cursor, Grok, Codex, or any MCP client.
Works with: Claude Code, Claude Desktop, claude.ai, Cursor, Grok Build, VS Code, Windsurf, OpenAI Codex, and any MCP-compatible agent.
Built on the Virlo API. Virlo is a short-form social intelligence platform covering TikTok, YouTube Shorts, Instagram Reels, and Meta Ads across every niche.
What your agent can do
- Spot trends early: emerging trends, a daily trend digest, and the top viral videos of the last 48 hours
- Explain virality: break down why a specific video popped (hook, format, sound, timing)
- Research any niche: run a research agent that finds the top videos, creator outliers, and content patterns for a topic
- Monitor a niche every week: recurring research agents that surface rising sounds, hashtags, and creators
- Look up creators: profile, outlier videos, audience demographics and geography, posting cadence
- Find trending sounds and hashtags: breakout audio, sound usage history, hashtag growth
- Steal hooks that work: trending hooks and a searchable hook library
- Track over time: daily tracking of creators and videos with signal reports
Install
Skill (Claude Code, Cursor, Codex, Windsurf, and other agents)
npx skills add Virlo-AI/Virlo-Agent-Plugin
Two
00acdbee3a70OBSERVED · 2026-10-11Trust 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.
00acdbee3a70full audit observations/trust-audit/mcp-server/virlo-ai__virlo-agent-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 |
|---|---|---|---|---|---|
| 2026-10-11 | 00acdbee3a70 | SAFE | B | 89 | first audit |
Questions
What is the Virlo-Agent-Plugin MCP server?
Give your AI agent a social media brain: TikTok, YouTube Shorts & Instagram Reels trends, viral video analysis, creators, sounds & hashtags. MCP server + skills for Claude Code, Cursor, Codex.
Is Virlo-Agent-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 Virlo-Agent-Plugin need?
No credential environment variables were found in its source, so it appears to need none.
How does Virlo-Agent-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 (00acdbee3a70), read on 2026-10-11. The repository is watched and re-audited when it changes.