Content by jack batzner (3)

Jack Batzner announces a public preview .NET package that adds governance controls to Model Context Protocol (MCP) servers via a single builder extension, covering startup tool scanning, identity-aware policy enforcement, response sanitization, and built-in audit/metrics so MCP tool calls can fail closed by default.

Jack Batzner shows how to add a governance layer to MCP-based AI agents in .NET using the Agent Governance Toolkit, including policy-driven tool-call authorization, security scanning of tool definitions, response sanitization to reduce prompt-injection risk, and built-in audit/telemetry via OpenTelemetry.

Jack Batzner explains why MCP-based agent tool execution needs a governance layer, then introduces the open-source Agent Governance Toolkit (AGT) for deterministic policy checks, tool definition scanning, response inspection, identity/trust, and audit logging to reduce common agentic and MCP-specific security risks.