MCP
Introduction
Cerbera supports the Model Context Protocol (MCP) on both sides of the AI workflow:
- Cerbera MCP Server: connect Claude, Cursor, Claude Code, and other MCP-compatible clients to Cerbera so your AI assistant can run Cerbera AI workflows on your behalf, such as triaging alerts or adding rules.
- MCP Governance: discover every MCP server running on employee devices, set allow and block rules, and review activity from one dashboard as part of Cerbera AI.
Key Features
Connect to Cerbera
Run Cerbera workflows from Claude, Cursor, Claude Code, and more
MCP Governance
Detect, allow, and block MCP servers across your organization
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:
- Productivity: customers want their AI assistant to act on Cerbera AI data (triage an alert, add a rule, approve an exception).
- Security: security teams need visibility and policy over which MCP servers employees install and what those servers can access.
Cerbera addresses both in one place.
Getting Started
Connect your AI client
Point Claude, Cursor, or Claude Code at the Cerbera MCP server to unlock workflows like Triage AI Alerts and Add or Update a Rule. See Connect to Cerbera.
Deploy the Cerbera proxy
Install the Cerbera proxy so MCP activity on employee laptops is observable. See Deployment.
Set MCP policies
In Cerbera AI, choose a default policy (allow or block new MCP servers) and add per-server rules. See MCP Governance.
Review activity
Monitor tool calls, token exposure, and policy violations from the MCP dashboard.