Typescript

MCP OAuth Metadata Bypass: How a Malicious Server Steals Your Credentials Through Discovery

13 March 2026·10 mins

Vulnerability Research Bug Bounty Mcp Oauth Credential-Theft Vulnerability-Research Responsible-Disclosure Bug-Bounty Python Typescript

Sixth article in my MCP security series. A malicious MCP server can poison OAuth Authorization Server Metadata to redirect token exchange, client registration, and PKCE verifiers to attacker-controlled endpoints — while the user sees a legitimate identity provider login page. The Python and TypeScript SDKs skip RFC 8414 Section 3.3 issuer validation and perform no endpoint origin checks. Reported to Anthropic VDP, closed as duplicate of an existing tracked issue. Full technical breakdown and PoC.

MCP SSRF via OAuth PRM Discovery: How a 401 Turns Your Client Into a Proxy

27 February 2026·8 mins

Vulnerability Research Bug Bounty Mcp Ssrf Oauth Vulnerability-Research Responsible-Disclosure Bug-Bounty Python Typescript

Second article in my MCP security series. A malicious MCP server returns a 401 with a crafted WWW-Authenticate header pointing resource_metadata at any URL it wants. The MCP SDK fetches that URL without origin validation, resulting in blind SSRF that affects both Python and TypeScript SDKs, Claude Desktop, and Claude Code. Reported to Anthropic VDP, closed as duplicate. Full technical details disclosed here.

↑