AI SDK 5 Migration MCP Server
Helps migrate projects from AI SDK 4.x to 5.0 by generating a migration checklist and searching the official migration guide for code and data changes.
README
AI SDK 5 Migration MCP Server
An MCP server that helps you migrate from AI SDK 4.x to 5.0. This server has been designed to work with Cursor, but should work with any compatible MCP client.
Quick Start
Step 1: Configure Cursor
Create or edit .cursor/mcp.json in your project:
{
"mcpServers": {
"ai-sdk-5-migration": {
"url": "https://ai-sdk-5-migration-mcp-server.vercel.app/api/mcp"
}
}
}
After saving the configuration, open the command palette (Cmd+Shift+P) and search for "View: Open MCP Settings". Verify that the new server appears in the list and is toggled to on.
Want to run it locally? See the Local Development section below.
Step 2: Run the migration
Open your project in Cursor and use this prompt:
Please migrate this project to AI SDK 5 using the ai-sdk-5-migration mcp server. Start by creating a checklist.
This prompt will:
- Create a comprehensive migration checklist (
AI_SDK_5_MIGRATION.md) - Guide the agent through all migration steps systematically
- Search the official migration guides when needed for specific changes
Note: This has been tested with Cursor's auto model setting
How It Works
This server provides three MCP tools:
-
create-checklist- Returns a curl command that downloads a comprehensive migration checklist toAI_SDK_5_MIGRATION.md. This is much more efficient than having the model generate ~800 lines of text. -
search-guide- Searches the official AI SDK 5 migration guide for code-related changes (APIs, imports, streaming, tools, etc.). Returns the most relevant sections with examples. -
search-data-guide- Searches the data migration guide for database and persistence information (converting stored messages, dual-write patterns, schema changes).
The agent uses these tools automatically when you run the prompt above.
Local Development
If you prefer to run the server locally:
pnpm install
pnpm dev
Then update your .cursor/mcp.json to use http://localhost:3000/api/mcp instead of the hosted version.
Resources
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.