diff --git a/src/labs/deep-agents/built-in-components.mdx b/src/labs/deep-agents/built-in-components.mdx
index 1408dbb4..0b01ca78 100644
--- a/src/labs/deep-agents/built-in-components.mdx
+++ b/src/labs/deep-agents/built-in-components.mdx
@@ -58,3 +58,35 @@ Built-in support for calling specialized sub-agents with the following:
 - **Tool access control**: Subagents can have different tool sets
 
 A general-purpose sub-agent with the same instructions and tools as the main agent is always available.
+
+## MCP
+
+The `deepagents` library can be ran with MCP tools. This can be achieved by using the [Langchain MCP Adapter library](https://github.com/langchain-ai/langchain-mcp-adapters).
+
+For example:
+
+```python
+# pip install langchain-mcp-adapters
+
+import asyncio
+from langchain_mcp_adapters.client import MultiServerMCPClient
+from deepagents import create_deep_agent
+
+async def main():
+    # Collect MCP tools
+    mcp_client = MultiServerMCPClient(...)
+    mcp_tools = await mcp_client.get_tools()
+
+    # Create agent
+    agent = create_deep_agent(tools=mcp_tools, ....)
+
+    # Stream the agent
+    async for chunk in agent.astream(
+        {"messages": [{"role": "user", "content": "what is langgraph?"}]},
+        stream_mode="values"
+    ):
+        if "messages" in chunk:
+            chunk["messages"][-1].pretty_print()
+
+asyncio.run(main())
+```
diff --git a/src/labs/deep-agents/configuration-options.mdx b/src/labs/deep-agents/configuration-options.mdx
index 27a20d91..de705a97 100644
--- a/src/labs/deep-agents/configuration-options.mdx
+++ b/src/labs/deep-agents/configuration-options.mdx
@@ -89,4 +89,34 @@ const agent = createDeepAgent({
 });
 ```
 
-</CodeGroup>
\ No newline at end of file
+</CodeGroup>
+
+### Custom models
+
+<Note>
+
+Custom models are only supported in the Python implementation.
+
+</Note>
+
+By default, `deepagents` uses `"claude-sonnet-4-20250514"`. You can customize this by passing any [LangChain model object](https://python.langchain.com/docs/integrations/chat/).
+
+For example, use OpenAI's `gpt-oss` model via Ollama:
+
+```python
+# pip install langchain langchain-ollama
+
+from deepagents import create_deep_agent
+
+# ... existing agent definitions ...
+
+model = init_chat_model(
+    model="ollama:gpt-oss:20b",  
+)
+agent = create_deep_agent(
+    tools=tools,
+    instructions=instructions,
+    model=model,
+    ...
+)
+```
\ No newline at end of file