How to manage shared and user credentials with Managed Deep Agents Connections
Sep 9, 2026LangChain
Summary
This post details three methods for managing credentials and secrets for Managed Deep Agents (MDA) to interact with external tools and data. It covers agent-owned secrets (a single shared key), user-owned OAuth through MCP (using Linear as an example), and user-owned OAuth with a custom application. The talk demonstrates the MDA connections CLI for creating and managing connections, LangSmith Studio for running tools and triggering OAuth flows, and the process of registering OAuth apps in the connections catalog. It also shows how to write custom tools that leverage user tokens for actions like searching and creating issues.
More from the Agent Memory Management trail
- How to go from your agent's traces to a fine-tuned model in one workflow
- Introducing LangSmith Trajectories: A readable view of every agent session
- Introducing LangSmith Engine v2: Detect and ship fixes to agents faster
- Introducing LangSmith Custom Apps: Build custom interfaces around your agent data
- Schedules for Managed Deep Agents: Cron jobs, prompts, and Slack delivery