mcp
Safeguard articles tagged "mcp" — guides, analysis, and best practices for software supply chain and application security.
64 articles
MCP tool poisoning: hidden instructions and rug-pulled tool definitions
Tool-poisoning attacks against Model Context Protocol servers hide adversarial instructions inside tool descriptions and silently mutate tool definitions after install. Here is how the attack works and how to defend against it.
When the Vulnerability Is the Design: MCP STDIO Command Injection Across 150M Downloads (May 2026)
OX Security documented command injection through the MCP STDIO transport across Python, TypeScript, Java, and Rust SDKs. Anthropic calls the behavior by-design and won't patch upstream. That leaves the fix to thousands of downstream projects.
MCPwn (CVE-2026-33032): One Missing Auth Check Turned nginx-ui's MCP Endpoint Into Unauthenticated RCE
nginx-ui added MCP support and split it across two HTTP routes. One route shipped without the auth middleware. The result is a CVSS 9.8 unauthenticated takeover, actively exploited, fixed with 27 characters of code.
Line Jumping: How MCP Tool Descriptions Attack Before Tools Are Called
Trail of Bits coined 'line jumping' for prompt injection delivered through MCP tool descriptions on connection. It bypasses every tool-invocation guardrail by design.
Securing MCP Servers Without Killing Developer Velocity
MCP servers are spreading inside engineering orgs faster than security teams can review them. Here is how to govern them without slowing teams down.
Enterprise MCP Registry Onboarding Process
A repeatable onboarding flow for adding MCP servers to an enterprise registry without becoming the team that says no to everything.
A Security Baseline for AI Agent Tool Use in 2026
Tool-using agents are now in production at most large organizations. The security baseline that should be table stakes, and what teams are still missing.
Scoped Credentials Per MCP Server: A Pattern
Long-lived shared tokens are the wrong unit of trust for MCP servers. Here is the per-server scoped-credential pattern and how to roll it out.
Tool-Call Audit: The Missing AI Observability Layer
Most AI observability stacks log prompts and completions. The actual security signal is in the tool calls. Here is how to capture it.
Out-Of-Band Confirmation For Irreversible Tool Calls
Some tool calls cannot be undone. Out-of-band confirmation is the cheapest defense for that small set, and the most expensive thing to skip.
How to Secure AI Agents on the MCP Protocol
MCP gives AI agents real tools, real credentials, and real blast radius. Here is a hardening guide for running MCP servers in production without torching your environment.
Claude MCP Tool Poisoning Threat Model 2026
A senior engineer's threat model for Claude MCP tool poisoning in 2026, covering malicious servers, description hijacking, and the authorization patterns that actually help.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.