Letting users trust their own MCP clients, without opening a phishing hole

This article explores the security challenges of Model Context Protocol (MCP) clients, specifically regarding OAuth redirect URI vulnerabilities. It highlights the tension between allowing user flexibility in self-hosted agents and maintaining secure, allowlisted authentication environments.
Why it matters
As AI agents become more integrated with personal data, solving the 'phishing hole' in authentication protocols is critical for preventing unauthorized access to sensitive user storage.
November 4, 2026 · Alexander Loginov · 10 min read
You run your own agent: a Slack bot, a service on a VPS, an MCP client you wrote over a weekend. You want it on your files, which on Stream Vessel means your own S3 bucket, where an agent can read, write and delete through the MCP server. The agent speaks MCP’s standard OAuth sign-in: it registers itself, opens a browser, you click Approve, it gets a token.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in