Skip to main content
When MCP Watch identifies shadow servers, follow this response framework to assess risk and take appropriate action.

Triage by Risk Level

Risk LevelIndicatorsResponse
CriticalUnknown/suspicious source, broad permissions, external data exfiltration endpointsImmediate removal, incident response, credential rotation
HighThird-party MCP not in catalog, access to sensitive dataBlock via MDM, require security review before approval
MediumKnown vendor but not approved, limited scopeUser education, migrate to Runlayer-managed version
LowKnown safe MCP, read-only access, internal onlyDocument and monitor, encourage migration to Runlayer

Investigation Checklist

  1. Identify the user and their role
  2. Determine when the MCP was configured
  3. Review the MCP’s stated purpose and actual capabilities
  4. Check if the MCP connects to external endpoints
  5. Assess what data the MCP could access
  • Is it from a known vendor (GitHub, Slack, etc.)?
  • Is it an open-source project? Check repository activity and maintainers
  • Is it internally developed? Verify with the development team
  • Are there any known vulnerabilities or security advisories?
  • Does the user have a legitimate business reason?
  • Could an existing Runlayer-managed MCP fulfill the need?
  • Is this a one-off or widespread usage pattern?
  • Migrate: Help user set up equivalent Runlayer-managed MCP
  • Approve: Submit for formal review and add to catalog
  • Remove: Use MDM to remove configuration from device
  • Block: Add to blocklist if malicious or prohibited

Response Workflow