Integration · Developer tools

Connect Claude & ChatGPT to Intruder

Ask your AI which critical vulnerabilities are open, where an issue occurs, or to start a scan in Intruder. It can list issues by severity and tag, show the affected targets and ports, and read raw scanner output and comments. It can also add targets and tags, start or cancel scans, and comment on or snooze an occurrence.

Connect Intruder free

Free plan, no credit card. Takes about a minute.

Try asking

“Which critical issues are open right now?”
The AI lists open issues filtered on critical severity.
“Where does issue 1234 occur?”
It lists the occurrences of the issue with the affected targets and ports.
“Show me the scanner output for the occurrence on port 443.”
It reads the raw scanner output for that occurrence so you can see what was found.

What your AI can do

Issues and occurrences

List open issues by severity, date, tag or snooze status, see where each one occurs, and read scanner output and fixed occurrences.

Targets and tags

List targets and tags, add new targets with tags, tag existing targets and delete targets you no longer scan.

Scans and licences

List scans and schedules, start a scan for all or some targets, cancel a running scan and check your licences.

“Add staging.example.com as a target with the tag staging.”
It creates the target with the address and tag, so it is included in future scans.
“Scan all targets tagged production now.”
It starts a scan of the targets with that tag and reports the scan so you can follow its status.
“Snooze that occurrence for 30 days, it is behind our VPN.”
It snoozes the occurrence with the reason, details and duration, so it stops being reported.

18 tools for Intruder

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

add_occurrence_commentVisible to othersAdd a comment to an occurrence by `issue_id` and `occurrence_id`.
add_target_tagChanges dataAdd a tag to a target by `target_id`.
cancel_scanDeletesCancel a running scan by `id`. This cannot be undone.
create_targetChanges dataAdd a target to scan by `address`, with optional `tags`.
delete_targetDeletesPermanently delete a target by `id`. It is no longer scanned.
get_occurrence_scanner_outputGet the raw scanner output for one occurrence by `issue_id` and `occurrence_id`.
get_scanGet one scan by `id`, including its status and targets.
list_fixed_occurrencesList occurrences that have been fixed.
list_issue_occurrencesList where an issue occurs (the affected targets and ports) by `issue_id`.
list_issuesList open vulnerability issues, filtered by `severity`, `since`, `snoozed`, `tag_names` or `issue_ids`.
list_licensesList your licences and how many targets they allow.
list_occurrence_commentsList the comments on an occurrence by `issue_id` and `occurrence_id`.
list_scan_schedulesList scheduled scans.
list_scansList scans with their status.
list_tagsList the tags used on your targets.
list_targetsList your scan targets (domains, IPs and apps).
snooze_occurrenceVisible to othersSnooze an occurrence by `issue_id` and `occurrence_id` so it stops being reported, with a `reason`, `details` and optional `duration`.
start_scanChanges dataStart a scan now, for specific `target_addresses` or targets with `tag_names`; leave both out to scan all targets. Uses your licence.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Intruder from the app list.
2
Paste your key
Paste an Intruder personal access token. In the Intruder portal open My account, go to the API Access Tokens section and create a personal access token. Copy it when it is shown.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Intruder?

The AI can read issues, occurrences, scanner output, comments, fixed occurrences, targets, tags, scans, scan schedules and licences. It can add targets and tags, start and cancel scans, comment on an occurrence, snooze an occurrence and delete a target.

Does the AI see my Intruder credentials?

No. Your Intruder credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start by only reading issues. Cancelling a scan and deleting a target cannot be undone, and snoozing hides an occurrence from your reports, so these can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Intruder account.

Does starting a scan use my Intruder licence?

Yes. A scan started by the AI uses your Intruder licence in the same way as one started in the portal. The AI can list your licences and how many targets they allow before it starts a scan.