laguagu/claude-code-nextjs-skills / skills/ai-sdk-6
ai-sdk-6
VerifiedVercel AI SDK v6 development, for projects already on ai@6. Use when building or maintaining AI agents, chatbots, tool integrations, streaming apps, or structured output in a v6 codebase. New projects and ai@7 code use ai-sdk-7; an unknown version goes through ai-sdk. Covers ToolLoopAgent, useChat, generateText, streamText, tool approval, provider tools, MCP integration, and Output patterns.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.1 KB |
| references/agents.md | markdown | 1.0 KB |
| references/core-functions.md | markdown | 1.1 KB |
| references/examples.md | markdown | 787 B |
| references/mcp.md | markdown | 1009 B |
| references/middleware.md | markdown | 1.0 KB |
| references/tools.md | markdown | 1.9 KB |
| references/ui-hooks.md | markdown | 1.9 KB |
| references/workflows.md | markdown | 831 B |
references/mcp.md
View on GitHub# AI SDK 6 MCP integration
Use the compatible `@ai-sdk/mcp` client. Read installed transport and schema
types before wiring a remote server; production HTTP and SSE have different
lifecycle behavior from a local stdio process.
Discover only the tools the app is authorized to expose. Validate tool schemas,
credential handling and server identity; MCP discovery is not an authorization
decision. Keep remote endpoints under application policy rather than accepting
arbitrary user URLs.
Keep the MCP client alive for the whole tool loop. For non-streaming work, close
it in cleanup; for streaming, close it after completion/error/cancellation, not
immediately after returning the response.
Check provider/SDK support for resources, prompts and elicitation separately
from ordinary tool discovery. Set explicit bounds where remote calls can stall.
Read [v6 MCP tools](https://github.com/vercel/ai/blob/ai%406.0.297/content/docs/03-ai-sdk-core/16-mcp-tools.mdx) and
the installed `@ai-sdk/mcp` docs/source.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |