Intruder MCP server

What the model can do

Intruder vulnerability scanning: current issues by severity with where each occurs, fixed findings with when they were remediated, targets and when they were last scanned, scans and scan schedules, and the comments on an occurrence. Can comment on or snooze an occurrence, start or cancel a scan on named targets or tags, add, tag or delete a target, and create or delete a scan schedule.

Reads

• intruder_list_issuesCurrent vulnerabilities Intruder has found, one row per issue: title, severity, CVSS, exploit likelihood, category, first seen, whether snoozed…
• intruder_list_occurrencesWhere one Intruder issue occurs: each occurrence's stable occurrence_id, target address, port, protocol, CVEs, CVSS…
• intruder_list_fixedVulnerabilities Intruder has seen fixed: title, severity, host and port, CVSS, first seen, remediated at and due date.
• intruder_list_targetsTargets Intruder scans: address, type (external, internal, cloud, container image), status (live, unresponsive, unscanned, licence exceeded…)…
• intruder_list_scansIntruder scans: name, status (in progress, completed, cancelled…), type, schedule period and when created.
• intruder_list_occurrence_commentsComments on one occurrence of an Intruder issue, newest first, with who wrote each (a person or Intruder's assistant) and when.
• intruder_list_scan_schedulesIntruder's recurring scan schedules: id, name, period, status, next scan date, whether it scans every target, its targets and tags…

Acts, when you ask

These change something in Intruder. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

• intruder_add_occurrence_commentAdds a plain-text comment to one occurrence of an Intruder issue, as the token's user.
• intruder_snooze_occurrenceSnooze one occurrence of an Intruder issue, so it leaves the open issues and reports…
• intruder_start_scanStart an Intruder scan now on the named target addresses and/or tags (never every target: at least one is required).
• intruder_cancel_scanCancel a running Intruder scan by id (from intruder_list_scans).
• intruder_add_targetAdd a target (a host name, IP address or URL the company owns) to Intruder, optionally with tags.
• intruder_tag_targetAdd a tag to an Intruder target (by target id from intruder_list_targets).
• intruder_delete_targetDelete a target from Intruder (by target id from intruder_list_targets), so it is no longer scanned.
• intruder_create_scan_scheduleCreate a recurring Intruder scan schedule (daily, weekly, monthly or quarterly) for named target ids and/or tags, never every target.
• intruder_delete_scan_scheduleDelete an Intruder scan schedule (by id from intruder_list_scan_schedules), so its targets stop being scanned on that schedule.

Connect it

First connect Intruder on Dashboard → Connections, then add Memtro to your client once. The Intruder tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Intruder connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

• › Which critical vulnerabilities are open?
• › What did we fix last month?
• › Where does the OpenSSH issue occur?
• › Which targets are unresponsive?
• › Start a scan of the web-prod tag now that the patch is deployed.

Questions

Is this an official Intruder MCP server?

No. It is Memtro's MCP server with Memtro's Intruder connector behind it: the connector reads Intruder through its API with the credentials you connect on Dashboard → Connections, and Intruder publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

What does it cost?

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Intruder?

Only when you ask, and only what it has been granted: add a comment to a vulnerability occurrence; snooze a vulnerability occurrence (accepted risk, false positive or mitigating controls); start a scan on named targets or tags, or cancel a running scan; add a target to scanning, tag it, or delete it; create a recurring scan schedule for named targets or tags, or delete one. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Which clients work?

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Engineering and operations

• GitHub MCP server
• AWS CloudWatch MCP server
• Sentry MCP server
• ServiceNow MCP server
• Okta MCP server
• Twilio MCP server