MCP
Model Context Protocol
An open protocol connecting AI applications (clients) to servers that expose tools, resources and prompts. Revision 2026-07-28 is stateless and defines OAuth-based authorization for its HTTP transport.
- Defined in
- Model Context Protocol specification
Covered in
Constrain MCP and multi-agent trust boundaries
Validate each connection and delegated action without treating a token for another service, a tool description, another agent or a state handle as authority.
Secure AI-assisted development with coding assistants and agents
Treat generated code, suggested packages, repository text and MCP servers as untrusted inputs, and confine coding agents with OS-level isolation and short-lived, narrowly scoped credentials.
Secure the developer workstation: extensions, package managers, secrets and AI agents
Attackers reach the software supply chain through developers' editors, package installs and AI agents. Allow-list extensions, stop install scripts and brand-new versions, keep long-lived secrets off laptops, and lock down repository files that run code when a project opens.
Worked threat model: an LLM agent with tools
A complete worked threat model for an LLM agent with tools: the data-flow diagram, the threats from prompt injection, excessive agency, data exfiltration, confused-deputy and memory poisoning, and the mitigations, mapped to the OWASP Top 10 for LLM Applications 2026 and the OWASP Top 10 for Agentic Applications 2026.
Practice: Local project: Enforce retrieval and tool boundaries across crashes · Local project: Run model-generated Python in a locked-down container