Rapid7 InsightVM MCP server

What the model can do

Rapid7 InsightVM vulnerability management through the Insight Platform: assets with risk score, vulnerability counts by severity and tags, one asset's new, still-present and remediated findings, the vulnerability catalogue (CVEs, CVSS, exploits), scans, scan engines and sites. Can start a scan of named assets and stop a scan, each only when asked. Assets are named by host name and OS; their IP and MAC addresses, hardware identifiers and finding proof are never returned.

Reads

• rapid7_assetsSearch InsightVM assets: id, host name, operating system, type, risk score, vulnerability counts (critical, severe, moderate), exploits…
• rapid7_assetOne InsightVM asset by id, with its vulnerability findings: each finding's vulnerability id, status (e.g. VULNERABLE_EXPL), first and last found…
• rapid7_vulnerabilitiesSearch the InsightVM vulnerability catalogue (every check it can assess, not only what was found): id, title, severity, CVSS v3 and v2, risk score…
• rapid7_scansInsightVM scans started through the Insight Platform, or one scan by id: name, status, start and finish, and the engine used.
• rapid7_scan_enginesInsightVM scan engines: id, name, host name, status, when last seen and registered.
• rapid7_sitesInsightVM sites (the groups assets are scanned in), by name.

Acts, when you ask

These change something in Rapid7 InsightVM. 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.

• rapid7_start_scanStart an InsightVM vulnerability scan of the named assets now.
• rapid7_stop_scanStop a running InsightVM scan.

Connect it

First connect Rapid7 InsightVM on Dashboard → Connections, then add Memtro to your client once. The Rapid7 InsightVM 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 Rapid7 InsightVM 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 assets have the most critical vulnerabilities?
• › What has been remediated on the payroll server since last month?
• › Which assets are exposed to this CVE?
• › Which scan engines have not been seen recently?
• › Start a scan of the two new web servers

Questions

Is this an official Rapid7 InsightVM MCP server?

No. It is Memtro's MCP server with Memtro's Rapid7 InsightVM connector behind it: the connector reads Rapid7 InsightVM through its API with the credentials you connect on Dashboard → Connections, and Rapid7 InsightVM 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 Rapid7 InsightVM?

Only when you ask, and only what it has been granted: start a vulnerability scan of named assets (sends network probes to those machines); stop a running scan. 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