Merge pull request #59 from tisan-das/inference_model_access_resolution

Changed MCP client code example to support access token

Author: burtenshaw

units/en/unit2/gradio-client.mdx

@@ -54,6 +54,7 @@ Now, we can import the necessary libraries and create a simple Gradio interface
 
 ```python
 import gradio as gr
+import os
 
 from mcp import StdioServerParameters
 from smolagents import InferenceClientModel, CodeAgent, ToolCollection, MCPClient
@@ -69,10 +70,11 @@ tools = mcp_client.get_tools()
 ```
 
 Now that we have the tools, we can create a simple agent that uses them to answer questions. We'll just use a simple `InferenceClientModel` and the default model from `smolagents` for now.
-It is important to pass your api_key to the InferenceClientModel. You can access the token from your huggingface account. [check here.](https://huggingface.co/docs/hub/en/security-tokens).
+
+It is important to pass your api_key to the InferenceClientModel. You can access the token from your huggingface account. [check here.](https://huggingface.co/docs/hub/en/security-tokens), and set the access token with the environment variable  `HF_TOKEN`.
 
 ```python
-model = InferenceClientModel(api_key = YOUR_API_TOKEN)
+model = InferenceClientModel(token=os.getenv("HF_TOKEN"))
 agent = CodeAgent(tools=[*tools], model=model)
 ```
 
@@ -106,6 +108,7 @@ Here's the complete example of the MCP Client in Gradio:
 
 ```python
 import gradio as gr
+import os
 
 from mcp import StdioServerParameters
 from smolagents import InferenceClientModel, CodeAgent, ToolCollection, MCPClient
@@ -117,7 +120,7 @@ try:
     )
     tools = mcp_client.get_tools()
 
-    model = InferenceClientModel()
+    model = InferenceClientModel(token=os.getenv("HUGGINGFACE_API_TOKEN"))
     agent = CodeAgent(tools=[*tools], model=model)
 
     demo = gr.ChatInterface(