AI Security
Can an OpenAI Responses API call reach a private MCP server?
The Responses API reaches public MCP servers by URL and private ones through a tunnel. Learn what that means for security tools, with steps and a table.
Oct 19, 20266 min read
Resources
Supply Chain Security, in plain English.
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
Filter
Articles
RSS feedAI Security
Does OpenAI retain MCP tool data? What store=true means
OpenAI's docs say store=true keeps data 30 days unless zero data retention applies, and MCP servers have their own policies. What security teams check.
Oct 19, 20266 min read
AI Security
How do OpenAI Code Interpreter containers expire and handle files?
OpenAI Code Interpreter runs in sandboxed containers that expire after 20 idle minutes. How lifetime, memory tiers, and files affect security design.
Oct 19, 20267 min read
AI Security
ONNX custom operators: when a model needs a native library to run
ONNX Runtime custom operators are native code shipped as a shared library. What that means for model intake, and the questions to ask before you load one.
Oct 19, 20264 min read
AI Security
Why are wildcard scopes dangerous for AI agent tokens?
Scopes like all or admin star hand an AI agent every tool at once. What the MCP guidance says about scope minimization and how to design smaller scopes.
Oct 19, 20263 min read
AI Security
Offboarding AI coding assistants and MCP configs for leavers
When a developer leaves, also revoke AI assistant seats, API keys and MCP server credentials, and check agent configs for tokens tied to that person.
Oct 19, 20264 min read
AI Security
What does NYDFS AI guidance mean for teams using AI tools?
NYDFS's October 2024 AI letter applies Part 500 controls to AI: risk, vendors, access, training, monitoring. A checklist.
Oct 19, 20264 min read
AI Security
Narrow tools or a general shell for AI agents: which is safer?
Narrow, purpose built tools are easier to scope, approve and audit than a general shell or fetch tool. A comparison and a path to replace open ended tools.
Oct 19, 20263 min read
AI Security
MCP versus a REST API for security tools: what is the difference?
A REST API is built for programs written by developers, while MCP lets an AI assistant discover and call tools itself. A comparison for security buyers.
Oct 19, 20266 min read
Stay informed
Weekly insights on software supply chain security, delivered to your inbox.
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.