More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Agent SDK and MCP Breaking-Change Migration Playbook

    1

    **`@modelcontextprotocol/sdk` v1.x to v2.4+ Split (`@modelcontextprotocol/server` & `@modelcontextprotocol/client`):** - Rewrites imports for the v2 package split (`v2.4.0`).

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AI Agent SDK and MCP Breaking-Change Migration Playbook

    AI Agent SDK and MCP Breaking-Change Migration Playbook

    Example session with this skill installed

    Migrate our TypeScript MCP server and Vercel AI SDK agent from @modelcontextprotocol/sdk v1.12 (SSEServerTransport) and ai v5 (maxSteps + parameters) to @modelcontextprotocol/server v2.4.0 and ai v7.0.154.

    • Read your context and instructions
    • Compiled the ai agent sdk

    Migration Plan Executed

    1. Upgraded Dependencies in package.json:

      • Replaced @modelcontextprotocol/sdk (^1.12.0) with @modelcontextprotocol/server@2.4.0 and @modelcontextprotocol/client@2.4.0.
      • Upgraded ai to 7.0.154, @ai-sdk/openai to 4.0.103, and added @ai-sdk/mcp@2.0.85.
    2. Refactored src/mcp-server.ts (v1 SSE -> v2.4.0 Streamable HTTP):

    - import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
    - import { SSEServerTransport } from "@modelcontextprotocol/sdk/server/sse.js";
    + import crypto from "node:crypto";
    + import { McpServer, StreamableHTTPServerTransport } from "@modelcontextprotocol/server";
    
    - server.tool("lookup_user", { userId: z.string() }, async ({ userId }) => ({
    + server.registerTool("lookup_user", {
    +   title: "Lookup User",
    +   description: "Fetch user record by ID",
    +   inputSchema: z.object({ userId: z.string() }),
    +   annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: false }
    + }, async ({ userId }) => ({
        content: [{ type: "text", text: JSON.stringify({ userId, active: true }) }]
      }));
    
    - app.get("/sse", async (req, res) => {
    -   transport = new SSEServerTransport("/messages", res);
    -   await server.connect(transport);
    - });
    + const transport = new StreamableHTTPServerTransport({
    +   sessionIdGenerator: () => crypto.randomUUID()
    + });
    + await server.connect(transport);
    + app.all("/mcp", async (req, res) => {
    +   await transport.handleRequest(req, res, req.body);
    + });
    
    1. Refactored src/agent.ts (Vercel AI SDK v5 -> v7.0.154):
    - import { generateText, tool, experimental_createMCPClient } from "ai";
    + import { generateText, tool, stepCountIs } from "ai";
    + import { createMCPClient } from "@ai-sdk/mcp";
    + import { StreamableHTTPClientTransport } from "@modelcontextprotocol/client";
    
    - const mcpClient = await experimental_createMCPClient({ transport: { type: "sse", url } });
    + const mcpClient = await createMCPClient({ transport: new StreamableHTTPClientTransport(new URL(url)) });
    
      const result = await generateText({
    -   model: openai("gpt-4o"),
    -   maxSteps: 5,
    +   model: openai.responses("gpt-5"),
    +   stopWhen: stepCountIs(5),
        tools: {
          ...(await mcpClient.tools()),
          pingHost: tool({
            description: "Ping host",
    -       parameters: z.object({ host: z.string() }),
    +       inputSchema: z.object({ host: z.string() }),
            execute: async ({ host }) => ({ ok: true, host })
          })
        },
        prompt: "Run diagnostics."
      });
    
    1. Post-Migration Verification:
      • tsc --noEmit: Passed with 0 errors.
      • Verified /mcp endpoint responds to initialize and tools/list over Streamable HTTP.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Ship Clean AI SDK & MCP Upgrades Without Hallucinated APIs

    Most coding agents trained on 2024 or 2025 documentation still generate deprecated SSEServerTransport boilerplate, maxSteps in Vercel AI SDK, result_type in PydanticAI, or archived @modelcontextprotocol/server-* configs. AI Agent SDK and MCP Breaking-Change Migration Playbook gives your coding agent 7 battle-tested reference playbooks with exact before/after diffs, AST refactoring rules, and verification checklists for the biggest 2026 breaking changes.

    What Is Inside (7 Complete Migration Playbooks)

    1. @modelcontextprotocol/sdk v1.x to v2.4+ Split (@modelcontextprotocol/server & @modelcontextprotocol/client):
      • Rewrites imports for the v2 package split (v2.4.0).
      • Migrates deprecated SSEServerTransport / SSEClientTransport to single-endpoint StreamableHTTPServerTransport / StreamableHTTPClientTransport.
      • Fixes v2.4.0 breaking wire changes: unwrapped result.structuredContent on 2025-11-25 connections, z.int() enforcement on x-mcp-header parameters (error -32020), and valid URI schemes on Ajv $id / $ref fields.
      • Includes Python mcp (v2.3.0) and fastmcp (v4.1.4) lifespan and streamable-http migrations.
    2. Archived @modelcontextprotocol/server-* Replacements:
      • Exact .mcp.json rewrites, environment variable mappings, and tool name translations for server-github -> https://api.githubcopilot.com/mcp/, server-puppeteer -> @playwright/mcp@0.0.83, server-postgres -> @bytebase/dbhub / @supabase/mcp-server-supabase@0.14.0, server-slack -> @korotovsky/slack-mcp-server, server-brave-search -> @brave/brave-search-mcp-server@2.1.4, server-filesystem@2.0.1 (read_text_file), mcp-server-fetch==2026.10.24, and mcp-server-sqlite==2025.4.25 (read_query / write_query).
    3. OpenAI Node v7.45.0 & Python v3.39.0 (Responses API):
      • Refactors legacy Chat Completions functions and beta.chat.completions.parse (response_format) to client.responses.create and client.responses.parse (text_format / zodTextFormat).
      • Migrates removed client.beta.threads Assistants polling loops to stateful Responses API calls using previous_response_id.
    4. Vercel AI SDK ai v5/v6 to v7.0.154 & @ai-sdk/mcp v2.0.85:
      • Converts maxSteps: N to stopWhen: stepCountIs(N).
      • Updates tool({ parameters }) to tool({ inputSchema }) and toolCall.args / toolResult.result to toolCall.input / toolResult.output.
      • Upgrades experimental_createMCPClient to @ai-sdk/mcp createMCPClient with StreamableHTTPClientTransport.
    5. @langchain/langgraph v1.5.3 & @langchain/mcp-adapters v2.0.1:
      • Converts legacy StateGraph({ channels }) definitions to Annotation.Root({ ... }) reducers.
      • Upgrades human-in-the-loop breakpoints to interrupt() and new Command({ resume }).
    6. Mistral v3.3.0, PydanticAI v2.62.0, & Claude Agent SDK v0.3.311:
      • Updates @mistralai/mistralai default MistralClient imports to named Mistral class and camelCase request fields.
      • Refactors pydantic-ai result_type -> output_type, result.data -> result.output, and @agent.result_validator -> @agent.output_validator.
      • Updates @anthropic-ai/claude-agent-sdk query() permissionMode / canUseTool callbacks and multi-turn thinking block signature preservation.
    7. Production .mcp.json Hardening Checklist:
      • Locks floating @latest tags, configures FASTMCP_LOG_LEVEL=ERROR to prevent stdio JSON-RPC framing corruption, enforces --read-only database flags, and verifies tools/list schema snapshots.

    Does not support automatic migration of custom, non-standard MCP transport implementations. Requires existing type definitions for accurate symbol detection.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 20 days ago

    Requires

    Python
    X Header MCP
    @playwright/mcp
    Node.js
    @bytebase/dbhub
    @brave/brave-search-mcp-server
    @org/pkg
    uv (Python tool runner)
    Chrome Devtools MCP
    Fetch MCP
    Adapters MCP
    @org/mcp-server

    Permissions

    Browser
    Read Files
    Network Access
    Environment Variables
    Listed20 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the transition from legacy 2024-2025 SDK patterns to 2026 standards, specifically addressing the deprecation of original MCP server packages and major breaking changes in frameworks like Vercel AI SDK v7.

    The skill supports both TypeScript/Node.js and Python environments, covering major libraries including OpenAI v7, LangGraph v1.5, PydanticAI v2, and the full MCP v2.4+ suite.

    Unlike generic LLMs that may hallucinate deprecated syntax, this skill uses the 'AgentBreakWatch' registry to provide verified, version-locked codemods that match the exact 2026 technical requirements.

    You receive the complete automated migration playbook, including before/after diff logic, transport layer refactoring templates for MCP v2, and a post-migration verification checklist for type-safety.

    The skill requires your project to have standard manifest files (like package.json or requirements.txt) and existing type definitions to accurately map and refactor deprecated symbols.

    New in Agents & Orchestration