<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Olivares AI — Blog</title><description>Technical writing on operating AI agents safely on real infrastructure: access mapping, least-privilege drift, auditing Claude Code and MCP, and self-hosted AI governance.</description><link>https://olivares.ai/</link><language>en</language><item><title>What your AI agents can actually reach: mapping agent access on real infrastructure</title><link>https://olivares.ai/blog/map-what-your-ai-agents-can-reach/</link><guid isPermaLink="true">https://olivares.ai/blog/map-what-your-ai-agents-can-reach/</guid><description>An AI agent holds credentials, is permitted some actions, and is observed doing others. The access map shows the gap — and where least-privilege quietly broke.</description><pubDate>Fri, 05 Jun 2026 00:00:00 GMT</pubDate><category>agent-access</category><category>least-privilege</category><category>observability</category><category>audit</category></item><item><title>Auditing Claude Code and MCP servers in self-hosted environments</title><link>https://olivares.ai/blog/auditing-claude-code-and-mcp-self-hosted/</link><guid isPermaLink="true">https://olivares.ai/blog/auditing-claude-code-and-mcp-self-hosted/</guid><description>How to build an auditor-grade trail for Claude Code and MCP servers without leaving your perimeter: per-agent identity, a hash-chained ledger, untrusted MCP signals.</description><pubDate>Thu, 28 May 2026 00:00:00 GMT</pubDate><category>MCP</category><category>Claude Code</category><category>audit</category><category>self-hosted</category></item><item><title>Least-privilege drift: catching over-privileged AI agents before an incident</title><link>https://olivares.ai/blog/least-privilege-drift-for-ai-agents/</link><guid isPermaLink="true">https://olivares.ai/blog/least-privilege-drift-for-ai-agents/</guid><description>AI agents accrue access faster than anyone reviews it. Learn to detect least-privilege drift with a permitted-vs-observed diff and policy enforced at access time.</description><pubDate>Wed, 20 May 2026 00:00:00 GMT</pubDate><category>least-privilege</category><category>ai-agents</category><category>policy-as-code</category><category>audit</category></item><item><title>Self-hosted AI governance and data residency: the strongest GDPR story</title><link>https://olivares.ai/blog/self-hosted-ai-governance-data-residency-gdpr/</link><guid isPermaLink="true">https://olivares.ai/blog/self-hosted-ai-governance-data-residency-gdpr/</guid><description>Why self-hosting an AI platform is the strongest data-residency posture under GDPR: the governance tool never receives your data. Edges, not payloads.</description><pubDate>Wed, 13 May 2026 00:00:00 GMT</pubDate><category>data-residency</category><category>gdpr</category><category>self-hosted</category><category>ai-governance</category></item><item><title>Passive discovery vs proxies: inventorying AI agents without sitting in the data path</title><link>https://olivares.ai/blog/passive-discovery-vs-proxies-ai-agents/</link><guid isPermaLink="true">https://olivares.ai/blog/passive-discovery-vs-proxies-ai-agents/</guid><description>Two ways to see your AI agents: an inline proxy with high blast radius, or passive discovery from logs, OpenTelemetry and an eBPF backstop. An honest tradeoff.</description><pubDate>Wed, 06 May 2026 00:00:00 GMT</pubDate><category>passive-discovery</category><category>observability</category><category>eBPF</category><category>least-privilege</category></item></channel></rss>