feat(unit2/smolagents): add MCP server tool collection example

unit2/smolagents/tools.ipynb

@@ -1217,6 +1217,65 @@
         "agent.run(\"Search for luxury entertainment ideas for a superhero-themed event, such as live performances and interactive experiences.\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "OhbVrpoiVgRV"
+      },
+      "source": [
+        "## Importing a Tool Collection from Any MCP Server\n",
+        "\n",
+        "`smolagents` also allows importing tools from the hundreds of MCP servers available on [glama.ai](https://glama.ai/mcp/servers) or [smithery.ai](https://smithery.ai). If you want to dive deeper about MCP, you can check our [free MCP Course](https://huggingface.co/learn/mcp-course/).\n",
+        "\n",
+        "We first need to install the `mcp` integration for `smolagents`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5IfLBcbfnoGM"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install \"smolagents[mcp]\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bJmTPSIAoCLr"
+      },
+      "source": [
+        "The MCP servers tools can be loaded in a `ToolCollection` object as follows. Alfred can, for instance, hook his agent straight into a PubMed-based MCP server to make sure Gotham's elite have a remedy ready for the morning after the party:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Z3aWZkSBvrjn"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "from smolagents import ToolCollection, CodeAgent\n",
+        "from mcp import StdioServerParameters\n",
+        "from smolagents import InferenceClientModel\n",
+        "\n",
+        "model = InferenceClientModel(\"Qwen/Qwen2.5-Coder-32B-Instruct\")\n",
+        "\n",
+        "server_parameters = StdioServerParameters(\n",
+        "    command=\"uvx\",\n",
+        "    args=[\"--quiet\", \"pubmedmcp@0.1.3\"],\n",
+        "    env={\"UV_PYTHON\": \"3.12\", **os.environ},\n",
+        ")\n",
+        "\n",
+        "with ToolCollection.from_mcp(server_parameters, trust_remote_code=True) as tool_collection:\n",
+        "    agent = CodeAgent(tools=[*tool_collection.tools], model=model, add_base_tools=True)\n",
+        "    agent.run(\"Please find a remedy for hangover.\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "source": [