mirror of
https://github.com/langchain-ai/deepagents.git
synced 2026-07-15 11:55:45 -04:00
Mason Daugherty
f2d955ebc5
`README.md` guidance now points readers toward the shared LangChain learning and community resources across the repo. Python install snippets also use `uv add` consistently instead of `pip install` or `uv pip install`. ## Changes - Added LangChain Academy and Code of Conduct links across package and example READMEs, using existing Resources sections where available and adding a short Resources section where needed. - Updated partner package quick-install snippets for Daytona, Modal, and Runloop to use `uv add`. - Updated example setup instructions to use `uv add deepagents-cli` and `uv add --editable .` for local installs. - Refreshed the root README intro so the JavaScript/TypeScript library link sits in the main overview and the Deep Agents Code install callout appears before Quickstart.
deploy-mcp-docs-agent
A documentation research agent deployed with deepagents deploy. It answers developer questions about LangChain, LangGraph, and Deep Agents by searching the live docs via MCP before relying on general knowledge.
Prerequisites
| Variable | Description |
|---|---|
ANTHROPIC_API_KEY |
Claude model access |
LANGSMITH_API_KEY |
Required for deploy |
Deploy
deepagents deploy
MCP servers are now workspace-level resources. Register the LangChain docs server once, then reference it in tools.json:
deepagents mcp-servers add --url https://docs.langchain.com/mcp --name docs-langchain
What to try
Once deployed, open the agent in LangSmith and ask it questions like:
"How do I configure memory in Deep Agents?""What's the difference between sync and async subagents?""Show me how to add an MCP server to deepagents.toml""What models are supported for deploy?"
The agent always searches the docs first and cites the page it found the answer on.
Query via SDK
from langgraph_sdk import get_client
client = get_client(url="https://<your-deployment-url>")
thread = await client.threads.create()
async for chunk in client.runs.stream(
thread["thread_id"], "agent",
input={"messages": [{"role": "user", "content": "How do I add an MCP server to deepagents.toml?"}]},
stream_mode="messages",
):
print(chunk.data, end="", flush=True)
Find your deployment URL in LangSmith under Deployments. See the LangGraph SDK docs for more.
Structure
deploy-mcp-docs-agent/
├── AGENTS.md # Agent instructions and answer format
└── agent.json # Deploy config (name, model)
Resources
- deepagents deploy docs
- MCP server docs
- LangChain Academy — Comprehensive, free courses on LangChain libraries and products, made by the LangChain team.
- Code of Conduct — community guidelines and standards