@caspar_br: Agent auth is hard, but it shouldn't be! Your agent needs to act as someone: sometimes that's one shared identity, some…
Summary
Managed Connections simplifies OAuth for AI agents by allowing them to define their identity in code, avoiding complex authentication flows. Now available in managed-deepagents 0.7.
View Cached Full Text
Cached at: 09/08/26, 09:35 PM
Agent auth is hard, but it shouldn’t be!
Your agent needs to act as someone: sometimes that’s one shared identity, sometimes it’s the person asking. To get either right you’ll need an OAuth app for each service, a token store, refresh logic, and a consent flow
Today we’re fixing this with Managed Connections: define who your agent acts as in code, and the rest is handled for you:
𝚊𝚐𝚎𝚗𝚝 -> agent uses its own token 𝚞𝚜𝚎𝚛 -> agent uses the user’s token, guiding them through the consent flow if they haven’t connected yet
With a single argument you avoid the whole OAuth dance. Available now, in 𝚖𝚊𝚗𝚊𝚐𝚎𝚍-𝚍𝚎𝚎𝚙𝚊𝚐𝚎𝚗𝚝𝚜 0.7
Similar Articles
@caspar_br: Connections offer a simple, elegant way to implement agent auth. We support agent and user (OBO) credentials in mda 0.7…
LangChain announces new Connection features in Managed Deep Agents 0.7, providing simple agent authentication with support for agent and user credentials to streamline deployment.
Connections: managed credentials and per-caller identity for Managed Deep Agents (8 minute read)
The article introduces 'Connections,' a feature in Managed Deep Agents that enables managed credentials and per-caller identity for secure agent actions, supporting both static secrets and OAuth grants.
How are you handling agent identity and auth without handing over primary accounts?
A developer promotes Decoy (decoys.me), a product that gives AI agents scoped, revocable task-specific identities instead of direct access to primary accounts, featuring client-side encryption and a user-owned knowledge graph for cross-agent context sharing.
Should every agent get its own identity and credentials?
A discussion on whether AI agents should each receive their own identity and short-lived, scoped credentials instead of sharing a single API key, including how MCP servers fit into this model. The author invites real-world setups and lessons on when per-agent identities become overkill.
@LangChain: New in Managed Deep Agents 0.7: Connections
LangChain introduces new connection features in Managed Deep Agents 0.7 to simplify agent authentication via OAuth and token management.