MCP
Introduction
Cerbera addresses the Model Context Protocol (MCP) on both sides of the AI workflow:
- MCP Governance (available today): discover every MCP server running on employee devices, see a risk score for each, and enforce allow, monitor, redact, or block rules on MCP traffic, as part of Cerbera AI.
- Connect to Cerbera (roadmap): connect Claude, Cursor, Claude Code, and other MCP-compatible clients to Cerbera itself, so your AI assistant can run Cerbera AI workflows on your behalf, such as triaging alerts or drafting rules.
Key Features
MCP Governance
Detect, risk-score, and control MCP servers across your organization
Connect to Cerbera
Run Cerbera workflows from Claude, Cursor, Claude Code, and more (roadmap)
Why MCP?
MCP is the open protocol that lets AI assistants call external tools and APIs. Developers and operators now routinely connect AI clients to production systems, which introduces two needs:
- Security: security teams need visibility and policy over which MCP servers employees install and what those servers can access. Available today.
- Productivity: customers want their own AI assistant to act on Cerbera AI data (triage an alert, add a rule). On the roadmap.
Getting Started
Deploy the Cerbera proxy
Install the Cerbera proxy so MCP activity on employee laptops is observable. See Deployment.
Review the MCP inventory
Open the MCP Servers view inside AI Discovery to see every server in use and its risk score. See MCP Governance.
Add rules
Allow, monitor, or block specific MCP servers with Rules.
Review activity
Monitor tool calls and policy violations from the MCP Servers view and your alerts.