Enables AI clients to query controlled credential metadata, perform batch CRUD, and fill credentials into focused Windows fields or UTF-8 files by reference, without exposing secret values.
Enables AI agents to request and retrieve credentials from a Bitwarden-compatible vault through MCP tools, with human approvals, short-lived grants, audit logging, and optional OAuth 2.1 authentication. It also supports creating secrets and injecting them into child processes without exposing them to the model.
Credential vault for LLM agents that stores credentials encrypted and exposes MCP tools for authenticated HTTP requests, web scraping, and credential management, preventing AI assistants from seeing secrets.
Enables teams to securely store and retrieve credentials, view decrypted secrets or live OAuth tokens, and connect to third-party MCP servers through a unified MCP endpoint.