Hardcoded API keys, access tokens and other credentials used by AI coding tools have been found in publicly accessible MCP configuration files on GitHub, according to research from Hush Security’s The State of MCP Configuration: The Identity Security Gaps report. The company analyzed around 82,000 configuration files and found that 12% of credential slots contained a hardcoded credential literal, potentially exposing credentials for connected services and systems.
Hardcoded MCP credentials found in public GitHub files
About this summary. This is a short, independently written summary of an article first published by Help Net Security. Cyber Security News did not report or verify the underlying story. Read the original: https://www.helpnetsecurity.com/2026/09/18/hush-security-mcp-credential-exposure-report/

Source attribution: headline and facts are from Help Net Security (helpnetsecurity.com). Summary method: excerpt of the source description. See our source attribution policy and corrections policy.





