Get started

Virustotal for AI agents

VirusTotal scans files, URLs, and domains against many antivirus engines, used by security teams checking whether something is malicious before acting on it. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect VirustotalSee the 16 actions ↓
Security and identityAPI keyMCP + RESTvirustotal.com
AUDIT LOG · VIRUSTOTALPOLICY: acme-support
09:41:07 · claude · u_8f2read
virustotal.search
Search VirusTotal✓ allowed · 212ms
09:41:08 · claude · u_8f2read
virustotal.get_votes
Get Votes✓ allowed · 164ms
09:41:09 · claude · u_8f2write
virustotal.add_vote
Add Vote✓ approved · approved by user
EVERY VIRUSTOTAL CALL, ON THE RECORD
01 · USE CASES

What agents do in Virustotal.

01

Scan a URL

Submit a URL for analysis and get back a verdict from multiple scanning engines.

02

Get a file's report

Look up a file's scan history and detection results, a read-only lookup.

03

Get a domain's report

Check a domain's reputation and related activity before deciding whether to trust it.

02 · ACTIONS

16 Virustotal actions, graded by risk.

Every Virustotal action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

11

Look things up. Allowed by default.

  • virustotal.get_votes
    Get Votes
  • virustotal.get_analysis
    Get Analysis Report
  • virustotal.get_comments
    Get comments
  • virustotal.get_metadata
    Get VirusTotal Metadata
  • virustotal.get_url_report
    Get URL Report
  • virustotal.get_file_report
    Get File Report
  • virustotal.get_domain_report
    Get Domain Report
  • virustotal.get_ip_address_report
    Get IP Address Report
  • virustotal.get_domain_relationships
    Get Domain Relationships
  • virustotal.get_ip_address_relationships
    Get IP Address Relationships
  • virustotal.search
    Search VirusTotal

write

5

Create and change things. Allow, or ask the user first.

  • virustotal.add_vote
    Add Vote
  • virustotal.add_comment
    Add VirusTotal Comment
  • virustotal.scan_url
    Scan URL
  • virustotal.rescan_file
    Rescan File
  • virustotal.upload_file
    Upload File

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Virustotal in three steps.

  1. 01Your users connect VirustotalThey add their Virustotal api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “add Vote” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Virustotal through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('virustotal', {
  read: 'allow',
  write: 'ask',        // add_vote
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Virustotal connects.

Users add their Virustotal api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Virustotal connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Virustotal from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More security and identity apps.

1Password6 actionsAbuseIPDB6 actionsAnonyflow5 actionsDnsfilter170 actionsBorneo153 actionsDigicert101 actionsParadym69 actionsPersona69 actions
ALL SECURITY AND IDENTITY APPS →
07 · FAQ

Virustotal and Arc0, answered.

Q01

Can I use Virustotal with Claude, ChatGPT or Cursor?

Yes. Connect Virustotal to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Virustotal actions you allow.

Q02

How do users connect Virustotal?

Users add their Virustotal api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Virustotal actions can my agent take?

16 in total: 11 read, 5 write and 0 destructive, such as “add Vote”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Virustotal?

Yes. Allow read actions and deny writes in the Virustotal policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Virustotal too?

Yes. The same Virustotal connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Virustotal into your agent.

Your users connect Virustotal once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.

Connect VirustotalBrowse all apps →

Free to build · MCP + REST · Audit log on every plan