2026-06-30 routing exp 1

docs/client.md

@@ -35,7 +35,7 @@ import { StdioClientTransport } from '@modelcontextprotocol/client/stdio';
 
 ### Streamable HTTP
 
-For remote HTTP servers, use {@linkcode @modelcontextprotocol/client!client/streamableHttp.StreamableHTTPClientTransport | StreamableHTTPClientTransport}:
+For remote HTTP servers, use {@linkcode @modelcontextprotocol/client!client/modernStreamableHttp.StreamableHTTPClientTransport | StreamableHTTPClientTransport}:
 
 ```ts source="../examples/client/src/clientGuide.examples.ts#connect_streamableHttp"
 const client = new Client({ name: 'my-client', version: '1.0.0' });
@@ -49,7 +49,7 @@ For a full interactive client over Streamable HTTP, see [`simpleStreamableHttp.t
 
 ### stdio
 
-For local, process-spawned servers (Claude Desktop, CLI tools), use {@linkcode @modelcontextprotocol/client!client/stdio.StdioClientTransport | StdioClientTransport}. The transport spawns the server process and communicates over stdin/stdout:
+For local, process-spawned servers (Claude Desktop, CLI tools), use {@linkcode @modelcontextprotocol/client!client/modernStdio.StdioClientTransport | StdioClientTransport}. The transport spawns the server process and communicates over stdin/stdout:
 
 ```ts source="../examples/client/src/clientGuide.examples.ts#connect_stdio"
 const client = new Client({ name: 'my-client', version: '1.0.0' });
@@ -64,7 +64,7 @@ await client.connect(transport);
 
 ### SSE fallback for legacy servers
 
-To support both modern Streamable HTTP and legacy SSE servers, try {@linkcode @modelcontextprotocol/client!client/streamableHttp.StreamableHTTPClientTransport | StreamableHTTPClientTransport} first and fall back to {@linkcode @modelcontextprotocol/client!client/sse.SSEClientTransport | SSEClientTransport} on failure:
+To support both modern Streamable HTTP and legacy SSE servers, try {@linkcode @modelcontextprotocol/client!client/modernStreamableHttp.StreamableHTTPClientTransport | StreamableHTTPClientTransport} first and fall back to {@linkcode @modelcontextprotocol/client!client/sse.SSEClientTransport | SSEClientTransport} on failure:
 
 ```ts source="../examples/client/src/clientGuide.examples.ts#connect_sseFallback"
 const baseUrl = new URL(url);
@@ -113,7 +113,7 @@ console.log(systemPrompt);
 
 ## Authentication
 
-MCP servers can require authentication before accepting client connections (see [Authorization](https://modelcontextprotocol.io/specification/latest/basic/authorization) in the MCP specification). Pass an {@linkcode @modelcontextprotocol/client!client/auth.AuthProvider | AuthProvider} to {@linkcode @modelcontextprotocol/client!client/streamableHttp.StreamableHTTPClientTransport | StreamableHTTPClientTransport}. The transport calls `token()` before every request and `onUnauthorized()` (if provided) on 401, then retries once.
+MCP servers can require authentication before accepting client connections (see [Authorization](https://modelcontextprotocol.io/specification/latest/basic/authorization) in the MCP specification). Pass an {@linkcode @modelcontextprotocol/client!client/auth.AuthProvider | AuthProvider} to {@linkcode @modelcontextprotocol/client!client/modernStreamableHttp.StreamableHTTPClientTransport | StreamableHTTPClientTransport}. The transport calls `token()` before every request and `onUnauthorized()` (if provided) on 401, then retries once.
 
 ### Bearer tokens
 
@@ -162,7 +162,7 @@ For a runnable example supporting both auth methods via environment variables, s
 
 ### Full OAuth with user authorization
 
-For user-facing applications, implement the {@linkcode @modelcontextprotocol/client!client/auth.OAuthClientProvider | OAuthClientProvider} interface to handle the full authorization code flow (redirects, code verifiers, token storage, dynamic client registration). The {@linkcode @modelcontextprotocol/client!client/client.Client#connect | connect()} call will throw {@linkcode @modelcontextprotocol/client!client/auth.UnauthorizedError | UnauthorizedError} when authorization is needed — catch it, complete the browser flow, call {@linkcode @modelcontextprotocol/client!client/streamableHttp.StreamableHTTPClientTransport#finishAuth | transport.finishAuth(code)}, and reconnect.
+For user-facing applications, implement the {@linkcode @modelcontextprotocol/client!client/auth.OAuthClientProvider | OAuthClientProvider} interface to handle the full authorization code flow (redirects, code verifiers, token storage, dynamic client registration). The {@linkcode @modelcontextprotocol/client!client/client.Client#connect | connect()} call will throw {@linkcode @modelcontextprotocol/client!client/auth.UnauthorizedError | UnauthorizedError} when authorization is needed — catch it, complete the browser flow, call {@linkcode @modelcontextprotocol/client!client/modernStreamableHttp.StreamableHTTPClientTransport#finishAuth | transport.finishAuth(code)}, and reconnect.
 
 For a complete working OAuth flow, see [`simpleOAuthClient.ts`](https://github.com/modelcontextprotocol/typescript-sdk/blob/main/examples/client/src/simpleOAuthClient.ts) and [`simpleOAuthClientProvider.ts`](https://github.com/modelcontextprotocol/typescript-sdk/blob/main/examples/client/src/simpleOAuthClientProvider.ts).
 
@@ -599,14 +599,7 @@ For an end-to-end example of server-initiated SSE disconnection and automatic cl
 ## Tasks (experimental)
 
 > [!WARNING]
-> The tasks API is experimental and may change without notice.
-
-Task-based execution enables "call-now, fetch-later" patterns for long-running operations (see [Tasks](https://modelcontextprotocol.io/specification/latest/basic/utilities/tasks) in the MCP specification). Instead of returning a result immediately, a tool creates a task that can be polled or resumed later. To use tasks:
-
-- Call {@linkcode @modelcontextprotocol/client!experimental/tasks/client.ExperimentalClientTasks#callToolStream | client.experimental.tasks.callToolStream(...)} to start a tool call that may create a task and emit status updates over time.
-- Call {@linkcode @modelcontextprotocol/client!experimental/tasks/client.ExperimentalClientTasks#getTask | client.experimental.tasks.getTask(...)} and {@linkcode @modelcontextprotocol/client!experimental/tasks/client.ExperimentalClientTasks#getTaskResult | getTaskResult(...)} to check status and fetch results after reconnecting.
-
-For a full runnable example, see [`simpleTaskInteractiveClient.ts`](https://github.com/modelcontextprotocol/typescript-sdk/blob/main/examples/client/src/simpleTaskInteractiveClient.ts).
+> The tasks API has been removed from this version of the SDK. See the [Migration guide](./migration.md) for details.
 
 ## See also
 

docs/server.md

@@ -54,7 +54,7 @@ For a complete server with sessions, logging, and CORS mounted on Express, see [
 
 ### stdio
 
-For local, process-spawned integrations, use {@linkcode @modelcontextprotocol/server!server/stdio.StdioServerTransport | StdioServerTransport}:
+For local, process-spawned integrations, use {@linkcode @modelcontextprotocol/server!server/modernStdio.StdioServerTransport | StdioServerTransport}:
 
 ```ts source="../examples/server/src/serverGuide.examples.ts#stdio_basic"
 const server = new McpServer({ name: 'my-server', version: '1.0.0' });
@@ -498,15 +498,7 @@ server.registerTool(
 ## Tasks (experimental)
 
 > [!WARNING]
-> The tasks API is experimental and may change without notice.
-
-Task-based execution enables "call-now, fetch-later" patterns for long-running operations (see [Tasks](https://modelcontextprotocol.io/specification/latest/basic/utilities/tasks) in the MCP specification). Instead of returning a result immediately, a tool creates a task that can be polled or resumed later. To use tasks:
-
-- Provide a {@linkcode @modelcontextprotocol/server!index.TaskStore | TaskStore} implementation that persists task metadata and results (see {@linkcode @modelcontextprotocol/server!index.InMemoryTaskStore | InMemoryTaskStore} for reference).
-- Enable the `tasks` capability when constructing the server.
-- Register tools with {@linkcode @modelcontextprotocol/server!experimental/tasks/mcpServer.ExperimentalMcpServerTasks#registerToolTask | server.experimental.tasks.registerToolTask(...)}.
-
-For a full runnable example, see [`simpleTaskInteractive.ts`](https://github.com/modelcontextprotocol/typescript-sdk/blob/main/examples/server/src/simpleTaskInteractive.ts).
+> The tasks API has been removed from this version of the SDK. See the [Migration guide](./migration.md) for details.
 
 ## Shutdown
 

examples/client/README.md

@@ -35,7 +35,6 @@ Most clients expect a server to be running. Start one from [`../server/README.md
 | OAuth provider helper                               | Demonstrates reusable OAuth providers.                                                    | [`src/simpleOAuthClientProvider.ts`](src/simpleOAuthClientProvider.ts)                     |
 | Client credentials (M2M)                            | Machine-to-machine OAuth client credentials example.                                      | [`src/simpleClientCredentials.ts`](src/simpleClientCredentials.ts)                         |
 | URL elicitation client                              | Drives URL-mode elicitation flows (sensitive input in a browser).                         | [`src/elicitationUrlExample.ts`](src/elicitationUrlExample.ts)                             |
-| Task interactive client                             | Demonstrates task-based execution + interactive server→client requests.                   | [`src/simpleTaskInteractiveClient.ts`](src/simpleTaskInteractiveClient.ts)                 |
 
 ## URL elicitation example (server + client)
 

examples/client/src/simpleOAuthClient.ts

@@ -4,7 +4,7 @@ import { createServer } from 'node:http';
 import { createInterface } from 'node:readline';
 import { URL } from 'node:url';
 
-import type { CallToolResult, ListToolsRequest, OAuthClientMetadata } from '@modelcontextprotocol/client';
+import type { ListToolsRequest, OAuthClientMetadata } from '@modelcontextprotocol/client';
 import { Client, StreamableHTTPClientTransport, UnauthorizedError } from '@modelcontextprotocol/client';
 import open from 'open';
 
@@ -209,7 +209,6 @@ class InteractiveOAuthClient {
         console.log('Commands:');
         console.log('  list - List available tools');
         console.log('  call <tool_name> [args] - Call a tool');
-        console.log('  stream <tool_name> [args] - Call a tool with streaming (shows task status)');
         console.log('  quit - Exit the client');
         console.log();
 
@@ -229,10 +228,8 @@ class InteractiveOAuthClient {
                     await this.listTools();
                 } else if (command.startsWith('call ')) {
                     await this.handleCallTool(command);
-                } else if (command.startsWith('stream ')) {
-                    await this.handleStreamTool(command);
                 } else {
-                    console.log("❌ Unknown command. Try 'list', 'call <tool_name>', 'stream <tool_name>', or 'quit'");
+                    console.log("❌ Unknown command. Try 'list', 'call <tool_name>', or 'quit'");
                 }
             } catch (error) {
                 if (error instanceof Error && error.message === 'SIGINT') {
@@ -328,94 +325,6 @@ class InteractiveOAuthClient {
         }
     }
 
-    private async handleStreamTool(command: string): Promise<void> {
-        const parts = command.split(/\s+/);
-        const toolName = parts[1];
-
-        if (!toolName) {
-            console.log('❌ Please specify a tool name');
-            return;
-        }
-
-        // Parse arguments (simple JSON-like format)
-        let toolArgs: Record<string, unknown> = {};
-        if (parts.length > 2) {
-            const argsString = parts.slice(2).join(' ');
-            try {
-                toolArgs = JSON.parse(argsString);
-            } catch {
-                console.log('❌ Invalid arguments format (expected JSON)');
-                return;
-            }
-        }
-
-        await this.streamTool(toolName, toolArgs);
-    }
-
-    private async streamTool(toolName: string, toolArgs: Record<string, unknown>): Promise<void> {
-        if (!this.client) {
-            console.log('❌ Not connected to server');
-            return;
-        }
-
-        try {
-            // Using the experimental tasks API - WARNING: may change without notice
-            console.log(`\n🔧 Streaming tool '${toolName}'...`);
-
-            const stream = this.client.experimental.tasks.callToolStream(
-                {
-                    name: toolName,
-                    arguments: toolArgs
-                },
-                {
-                    task: {
-                        taskId: `task-${Date.now()}`,
-                        ttl: 60_000
-                    }
-                }
-            );
-
-            // Iterate through all messages yielded by the generator
-            for await (const message of stream) {
-                switch (message.type) {
-                    case 'taskCreated': {
-                        console.log(`✓ Task created: ${message.task.taskId}`);
-                        break;
-                    }
-
-                    case 'taskStatus': {
-                        console.log(`⟳ Status: ${message.task.status}`);
-                        if (message.task.statusMessage) {
-                            console.log(`  ${message.task.statusMessage}`);
-                        }
-                        break;
-                    }
-
-                    case 'result': {
-                        console.log('✓ Completed!');
-                        const toolResult = message.result as CallToolResult;
-                        for (const content of toolResult.content) {
-                            if (content.type === 'text') {
-                                console.log(content.text);
-                            } else {
-                                console.log(content);
-                            }
-                        }
-                        break;
-                    }
-
-                    case 'error': {
-                        console.log('✗ Error:');
-                        console.log(`  ${message.error.message}`);
-                        break;
-                    }
-                }
-            }
-        } catch (error) {
-            console.error(`❌ Failed to stream tool '${toolName}':`, error);
-        }
-    }
-
     close(): void {
         this.rl.close();
         if (this.client) {