Add Google GenAI Sampling Handler

docs/development/v3-notes/v3-features.mdx

@@ -23,6 +23,38 @@ result = await ctx.sample(
 )
 ```
 
+### Google GenAI Sampling Handler
+
+FastMCP now includes a sampling handler for Google's Gemini models ([#2977](https://github.com/jlowin/fastmcp/pull/2977)). This enables MCP clients to use Google's GenAI models with the sampling protocol, including full tool calling support.
+
+```python
+from fastmcp import Client
+from fastmcp.client.sampling.handlers import GoogleGenaiSamplingHandler
+from google.genai import Client as GoogleGenaiClient
+
+# Initialize the handler
+handler = GoogleGenaiSamplingHandler(
+    default_model="gemini-2.0-flash-exp",
+    client=GoogleGenaiClient(),  # Optional - creates one if not provided
+)
+
+# Use with MCP sampling (handler is configured at Client construction)
+async with Client("http://server/mcp", sampling_handler=handler) as client:
+    result = await client.sample(
+        messages=[...],
+        tools=[...],
+    )
+```
+
+Key features:
+- Converts MCP tool schemas to Google's function calling format
+- Supports all Google GenAI models that implement function calling
+- Handles nullable types, nested objects, and arrays in tool schemas
+- Properly maps tool choices (`auto`, `required`, `none`) to Google's configuration
+- Preserves model preferences from MCP sampling parameters
+
+The handler joins the existing Anthropic and OpenAI handlers, providing a consistent interface for model-agnostic sampling across providers.
+
 ### Concurrent Tool Execution in Sampling
 
 When an LLM returns multiple tool calls in a single sampling response, they can now be executed concurrently ([#3022](https://github.com/PrefectHQ/fastmcp/pull/3022)). Default behavior remains sequential; opt in with `tool_concurrency`. Tools can declare `sequential=True` to force sequential execution even when concurrency is enabled.

docs/python-sdk/fastmcp-client-sampling-handlers-google_genai.mdx

@@ -0,0 +1,17 @@
+---
+title: google_genai
+sidebarTitle: google_genai
+---
+
+# `fastmcp.client.sampling.handlers.google_genai`
+
+
+Google GenAI sampling handler with tool support for FastMCP 3.0.
+
+## Classes
+
+### `GoogleGenaiSamplingHandler` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/client/sampling/handlers/google_genai.py#L54" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
+
+
+Sampling handler that uses the Google GenAI API with tool support.
+

pyproject.toml

@@ -56,13 +56,14 @@ anthropic = ["anthropic>=0.40.0"]
 apps = ["prefab-ui>=0.6.0"]
 azure = ["azure-identity>=1.16.0"]
 code-mode = ["pydantic-monty>=0.0.7"]
+gemini = ["google-genai>=1.18.0"]
 openai = ["openai>=1.102.0"]
 tasks = ["pydocket>=0.18.0"]
 
 [dependency-groups]
 dev = [
     "dirty-equals>=0.9.0",
-    "fastmcp[anthropic,apps,azure,code-mode,openai,tasks]",
+    "fastmcp[anthropic,apps,azure,code-mode,gemini,openai,tasks]",
     # add optional dependencies for fastmcp dev
     "fastapi>=0.115.12",
     "opentelemetry-sdk>=1.20.0",