MCP-02

MCP & Tool Supply Chain

Securing the Model Context Protocol and agent tools — malicious servers, tool-description poisoning, CVE teardowns and sandboxing.

MCP trust boundary: agent connects to tools across an untrusted server, where one tool is poisoneduntrusted MCP serveragenttrusts resultstool calls / resultslist_filesread_urlrun_cmd ⚠ poisoned
Pillar

MCP Security: Tool Poisoning, Rogue Servers, and Supply-Chain Exploits

How attackers exploit the Model Context Protocol: tool poisoning, malicious and rogue MCP servers, rug pulls and supply-chain attacks against agent tooling — the offensive threat model.

Read

Other domains