Hackers Can Hijack Claude Code MCP Traffic to Steal OAuth Tokens

Cybersecuritynews •Guru Baran • June 8, 2026

A five-step attack chain that silently redirects Claude Code’s Model Context Protocol (MCP) traffic through attacker-controlled infrastructure, intercepting OAuth bearer tokens that grant persistent, broadly scoped access to connected SaaS platforms like Jira, Confluence, and GitHub with no patch incoming from Anthropic. Researchers at Mitiga Labs have demonstrated the attack, with the entry point being […]

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Claude Code MCP Traffic Hijacked to Steal OAuth Tokens A new man-in-the-middle (MitM) attack has been identified, targeting Anthropic's Claude Code ecosystem. Threat actors exploit vulnerabilities in the Model Context Protocol (MCP) traffic to intercept OAuth authentication tokens. This attack allows unauthorized access to enterprise SaaS platforms such as Jira, Confluence, and GitHub. Researchers from Mitiga Labs have detailed a five-step attack chain that redirects MCP traffic through attacker-controlled infrastructure. The attack leverages weak protections in the local Claude Code configuration file, specifically ~/.claude.json. As of now, no patch has been released by Anthropic to mitigate this vulnerability. Organizations using Claude Code are at risk of unauthorized access and data breaches. The attack is significant due to the potential for broad access to sensitive enterprise data. 3 sources 68

Hackers Can Hijack Claude Code MCP Traffic to Steal OAuth Tokens

The full story

Extracted Entities

Attack Types (1)

Platforms (3)