viralquerySAFE
ViralQuery agent skill and remote MCP distribution metadata
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
ViralQuery is a private video inspiration feed for one app, website, or niche. An agent saves a research brief and plain-English rules, runs bounded scrolls, and reads structured library, outlier, trend, and hook data.
Install the skill
npx --yes [email protected] add https://github.com/tfcbot/viralquery-skills/tree/083f6dac6b4cc2adb689aef99da55535bb4903b7/skills/viralquery --skill viralquery --copy
This pins both the installer CLI and the exact reviewed skill commit published with v2.2.0. Commit identities cannot move: review the next release diff, then replace the 40-character commit deliberately when upgrading. --copy leaves the agent with an independent copy instead of a mutable cache symlink.
Then ask:
Use $viralquery to verify my setup, set my app as the research workspace, look for organic demos with strong visual hooks, and run my first scroll.
The skill uses the protected ViralQuery HTTP API directly. It does not require MCP.
Configure VIRALQUERY_API_KEY in the agent's secret store or environment. If you also use the ViralQuery CLI, point it at the official API once:
viralquery auth --url https://api.viralquery.com
Keep VIRALQUERY_API_KEY out of command arguments and shell history. Custom deployments require an exact HTTPS origin plus explicit --allow-custom-origin; authenticated requests never follow redirects.
Get a key through viralquery.com/#pricing. The skill verifies the configured key with a protected request before it starts a scroll.
Optional remote MCP
Agents that support remote MCP can connect to https://viralquery.com/mcp with a ViralQuery API key in the bearer header. The MCP server exposes the same tenant workspace, rules, scroll, and bounded result workflow.
claude mcp add --transport http --scope user viralquery https://viralquery.com/mcp \ --header "Authorization: Bearer
ff703b999c27OBSERVED · 2026-10-13Trust 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.
ff703b999c27full audit observations/trust-audit/mcp-server/tfcbot__viralquery-skills.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 |
|---|---|---|---|---|---|
| 2026-10-13 | ff703b999c27 | SAFE | B | 89 | first audit |
Questions
What is the viralquery MCP server?
ViralQuery agent skill and remote MCP distribution metadata
Is viralquery 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 viralquery need?
No credential environment variables were found in its source, so it appears to need none.
How does viralquery 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 (ff703b999c27), read on 2026-10-13. The repository is watched and re-audited when it changes.