docs: stop presenting the in-memory client as the way to connect (#3443)

docs_src/caching/tutorial002.py

@@ -7,6 +7,7 @@ TOOLS = [Tool(name="forecast", input_schema={"type": "object"})]
 
 
 async def list_tools(ctx: ServerRequestContext[Any], params: PaginatedRequestParams | None) -> ListToolsResult:
+    print("tools/list served")
     return ListToolsResult(tools=TOOLS, ttl_ms=1_000)
 
 
@@ -15,3 +16,4 @@ server = Server(
     on_list_tools=list_tools,
     cache_hints={"tools/list": CacheHint(ttl_ms=60_000, scope="public")},
 )
+app = server.streamable_http_app()

docs_src/caching/tutorial003.py

@@ -1,39 +1,34 @@
 from dataclasses import dataclass
-from typing import Any
+
+import anyio
 
 from mcp import Client
 from mcp.client import CacheConfig
-from mcp.server import CacheHint, Server, ServerRequestContext
-from mcp.types import ListToolsResult, PaginatedRequestParams, Tool
+from mcp.types import ListToolsResult
 
 
 @dataclass
-class DemoState:
-    fetches: int = 0
-    now: float = 1_000_000.0
+class Clock:
+    now: float = 0.0
 
 
-state = DemoState()
+clock = Clock()  # advanced by hand below, so the TTL runs out without sleeping
 
 
-async def list_tools(ctx: ServerRequestContext[Any], params: PaginatedRequestParams | None) -> ListToolsResult:
-    state.fetches += 1
-    return ListToolsResult(tools=[Tool(name="forecast", input_schema={"type": "object"})])
-
-
-server = Server(
-    "Weather",
-    on_list_tools=list_tools,
-    cache_hints={"tools/list": CacheHint(ttl_ms=60_000, scope="public")},
-)
+async def run(client: Client) -> ListToolsResult:
+    tools = await client.list_tools()  # fetch 1
+    await client.list_tools()  # still fresh: served from the cache
+    clock.now += 2
+    await client.list_tools()  # past the one-second TTL: fetch 2
+    await client.list_tools(cache_mode="refresh")  # skip the cache read: fetch 3
+    return tools
 
 
 async def main() -> None:
-    start = state.fetches
-    async with Client(server, cache=CacheConfig(clock=lambda: state.now)) as client:
-        await client.list_tools()  # fetch 1
-        await client.list_tools()  # fresh for 60s: served from the cache
-        state.now += 60.0
-        await client.list_tools()  # the TTL ran out: fetch 2
-        await client.list_tools(cache_mode="refresh")  # skip the cache read: fetch 3
-        print(f"4 calls, {state.fetches - start} fetches")
+    async with Client("http://localhost:8000/mcp", cache=CacheConfig(clock=lambda: clock.now)) as client:
+        tools = await run(client)
+        print(tools.ttl_ms, tools.cache_scope)
+
+
+if __name__ == "__main__":
+    anyio.run(main)