1Password Allies With OpenAI to Secure Codex AI Coding Tool - DevOps.com
Briefly

1Password Allies With OpenAI to Secure Codex AI Coding Tool - DevOps.com
"As a result, Codex credentials can now be issued on a just-in-time basis to ensure secrets are not logged, cached, reused across sessions or surfaced in unexpected outputs. Instead of sharing .env files or hardcoding credential values, application developers access a shared environment where secrets are made available at runtime, without the values ever appearing in code, terminals, or model context."
"The MCP server does not read or return secret values through the MCP channel, surface secrets in the model's context window, or write them to disk. Codex can create environments, list variable names, and invoke applications that use those secrets, but the values themselves never leave the 1Password vault."
"Secrets remain encrypted and centrally managed, with access limited to authorized users who have been granted customized permissions, said Wang. Under no circumstances is credential data ever exposed to an AI agent or large language model (LLM) as plain text, she added."
"1Password is now making a case for managing the credentials granted to human developers and their AI agents via the same platform, said Wang. In time, 1Password will extend that reach to include multiple AI coding tools, she added."
An MCP server integrated with Codex enables just-in-time issuance of developer credentials to improve security. Secrets are provided at runtime through a shared environment rather than by sharing .env files or hardcoding values. The MCP channel does not read or return secret values, does not surface secrets in the model context window, and does not write them to disk. Codex can create environments, list variable names, and invoke applications that use those secrets while keeping the values inside the 1Password vault. DevSecOps teams can manage coding agents as a tenant with centralized, encrypted secret management and customized permissions. Credential data is not exposed to an AI agent or LLM as plain text, and the platform is positioned to support multiple AI coding tools over time.
Read at DevOps.com
Unable to calculate read time
[
|
]