π The fast, Pythonic way to build MCP servers and clients.
Update client features
Jeremiah Lowin3d2e2a5954df
diff --git a/docs/clients/client.mdx b/docs/clients/client.mdxindex e69d45e42..d246c88fe 100644--- a/docs/clients/client.mdx+++ b/docs/clients/client.mdx@@ -182,7 +182,7 @@ async with client:Explore the detailed documentation for each operation type:-### Core Interactions+### Core Operations- **[Tools](/clients/tools)** - Execute server-side functions and handle results- **[Resources](/clients/resources)** - Access static and templated resources- **[Prompts](/clients/prompts)** - Work with message templates and argument serializationdiff --git a/docs/clients/logging.mdx b/docs/clients/logging.mdxindex ff1a60893..a9ea86a48 100644--- a/docs/clients/logging.mdx+++ b/docs/clients/logging.mdx@@ -2,7 +2,7 @@title: Server LoggingsidebarTitle: Loggingdescription: Learn how to receive and handle log messages from MCP servers.-icon: file-text+icon: receipt---import { VersionBadge } from '/snippets/version-badge.mdx'diff --git a/docs/clients/progress.mdx b/docs/clients/progress.mdxindex cb9ee0031..f8dd9db1c 100644--- a/docs/clients/progress.mdx+++ b/docs/clients/progress.mdx@@ -2,7 +2,7 @@title: Progress MonitoringsidebarTitle: Progressdescription: Learn how to handle progress notifications from long-running server operations.-icon: chart-line+icon: bars-progress---import { VersionBadge } from '/snippets/version-badge.mdx'diff --git a/docs/clients/roots.mdx b/docs/clients/roots.mdxindex 2db66a37b..48c4aa258 100644--- a/docs/clients/roots.mdx+++ b/docs/clients/roots.mdx@@ -2,7 +2,7 @@title: Client RootssidebarTitle: Rootsdescription: Learn how to provide local context to MCP servers.-icon: tree+icon: folder-tree---import { VersionBadge } from '/snippets/version-badge.mdx'diff --git a/docs/clients/sampling.mdx b/docs/clients/sampling.mdxindex 887541698..0003999f4 100644--- a/docs/clients/sampling.mdx+++ b/docs/clients/sampling.mdx@@ -2,7 +2,7 @@title: LLM SamplingsidebarTitle: Samplingdescription: Learn how to handle server-initiated LLM sampling requests.-icon: brain+icon: robot---import { VersionBadge } from '/snippets/version-badge.mdx'@@ -40,15 +40,31 @@ client = Client(## Handler Parameters-The sampling handler receives:+The sampling handler receives three parameters:-- **`messages`**: List of `SamplingMessage` objects representing the conversation-- **`params`**: `SamplingParams` object with generation parameters (systemPrompt, maxTokens, temperature, etc.)-- **`context`**: `RequestContext` object with request metadata+### SamplingMessage++- **`role`**: Message role (e.g., "user", "assistant", "system")+- **`content`**: Message content (usually has `.text` attribute)++### SamplingParams++- **`systemPrompt`**: System prompt string (optional)+- **`maxTokens`**: Maximum tokens to generate (optional)+- **`temperature`**: Sampling temperature (optional)+- **`topP`**: Top-p sampling parameter (optional)+- **`stopSequences`**: List of stop sequences (optional)++### RequestContext++- **`request_id`**: Unique identifier for the sampling request## Basic Example```python+from fastmcp import Client+from fastmcp.client.sampling import SamplingMessage, SamplingParams, RequestContext+async def basic_sampling_handler(messages: list[SamplingMessage],params: SamplingParams,@@ -73,22 +89,3 @@ client = Client()```-## Accessing Parameters--```python-async def parameter_handler(- messages: list[SamplingMessage],- params: SamplingParams,- context: RequestContext-) -> str:- # Available parameters from the server- system_prompt = params.systemPrompt- max_tokens = params.maxTokens- temperature = params.temperature- top_p = params.topP- stop_sequences = params.stopSequences-- # Use these parameters with your LLM service- return "Generated response"-```-diff --git a/docs/docs.json b/docs/docs.jsonindex 90f983e72..d35476ca6 100644--- a/docs/docs.json+++ b/docs/docs.json@@ -95,7 +95,7 @@"pages": ["clients/client",{- "group": "Core Interactions",+ "group": "Core Operations","icon": "handshake","pages": ["clients/tools",