Now let's give it a tool! We host our docs on @mintlify
, which means we get an MCP server out of the box. Let's add that to our mcp.json file (You can see our full docs here: https://
docs.langchain.com)
AGENTS
-
LangChain adds MCP server tool for Mintlify documentation
By
–
-
Initializing DeepAgents Project with Repository Setup
By
–
Then I'm going to set up my repo. I'm going to run `deepagents init` It will ask me to give my project a name. I'm going to call it `lc-docs`. It will then set up scaffolding for my project
-
Configuring AI Agent with GLM5 Model via Baseten
By
–
After switching into the new directory (`cd lc-docs`) I'm going to set the name of my agent, and the model to use This is done in deepagents.toml I'm going to use @Zai_org GLM5 model, served via @baseten
-
Installing DeepAgents CLI for agent deployment
By
–
First I'm going to install deepagents cli. This is a CLI which will help me set up and then deploy my agent `uv tool install deepagents-cli` DeepAgents CLI is open source – see it here: https://
github.com/langchain-ai/d
eepagents/tree/main/libs/cli
… -
DeepAgents Deploy: No-Code Agent Production Deployment Platform
By
–
DeepAgents Deploy is the easiest way to bring agents to production, with just a few markdown and configuration files (no code!) Here's me building an agent that connects to LangChain Docs. Powered by @Zai_org GLM5 (via @baseten
) and @mintlify MCP -
Agent Latency Optimization: Router and Manager Bottlenecks
By
–
Agreed on both. Latency depends mostly on the agent blocks, not the connections themselves (those are basically free). With a decent local model the bottleneck is inference time per agent call, so the router and manager agents dominate. Most of the 29 edges are just data
-
Error Handling and Retry Mechanisms in AI Agent Blocks
By
–
Good question. Sim has retries and error paths built into each block, so you can set retry counts and route failures to a fallback branch. For the agent blocks, I also keep prompts strict on output format so downstream parsing doesn't break. Haven't needed heavy fallback
-
Agent Environment Architecture: Memory Routing Integration
By
–
Thanks! That framing is exactly how I started seeing it too. Once memory, routing, and multi-channel sit in one place, the workflow stops feeling like a script and starts feeling like an environment the agents actually live in.
-
AI-Generated Workflow Structures and Intelligent Branching Logic
By
–
Yeah, Mothership generated the structure from a prompt. For branching, it picks the right block (router for classification, condition for if/else, parallel for fan-out) and wires them up. I usually tweak the routes and prompts after, but the skeleton holds up surprisingly well.
-
Dual Memory Architecture: Short-term Manager and Long-term Supabase Retrieval
By
–
Hey, there are two memory layers running in parallel. Short-term lives on the manager agent (keyed to the user). Long-term embeds each turn into Supabase and pulls relevant past context back before the model sees the new message. State lives outside the model, so swapping