Integrate You.com web tools with Vercel AI SDK

Integrate Vercel AI SDK applications with You.com tools (web search, AI agent, content extraction). Use when developer mentions AI SDK, Vercel AI SDK, generateText, streamText, or You.com integration with AI SDK.

Security Scan

The skill's instructions match its stated purpose (adding You.com tools to Vercel AI SDK), but its metadata omits the API key requirement and it directs installing a third‑party npm package without declaring that dependency — this mismatch and supply‑chain risk are worth caution.

Purpose & Capability

The name/description claim to integrate You.com tools with the Vercel AI SDK, and the SKILL.md contains concrete examples and steps to do exactly that (install plugin, add youSearch/youExpress/youContents to generateText/streamText). The requested actions are coherent with the stated purpose.

Instruction Scope

The SKILL.md instructs the agent/developer to install an npm package, edit or create files that call generateText/streamText, and to reference an API key via process.env. Those instructions stay within the integration scope and do not ask to read unrelated system files or exfiltrate data, but they give the agent open-ended permission to modify user code (ask which files to edit) — expected for a code-integration helper but worth noting.

Install Mechanism

This is an instruction-only skill (no install spec). It tells the user to run a package manager command to install @youdotcom-oss/ai-sdk-plugin. There is no automated download/install specification in the skill bundle itself, which lowers platform risk, but it still relies on a third‑party npm package (supply‑chain risk) that the user will install locally.

Credentials

The SKILL.md expects a You.com API key (standard name YDC_API_KEY or a custom env var) and shows code using process.env, but the skill registry metadata lists no required environment variables or primary credential. That mismatch (instructions require a secret but metadata declares none) is an incoherence and makes it harder for users to audit what credentials the skill needs. Also, installing the plugin will cause runtime requests that require that API key; the metadata should explicitly declare this.

Persistence & Privilege

The skill does not request always:true, does not modify other skills' configs, and is user-invocable. It does not request elevated or persistent platform privileges.

What to consider before installing

This skill appears to do what it says (add You.com tools to Vercel AI SDK), but there are a few things to check before using it: - Metadata mismatch: The documentation requires a You.com API key (YDC_API_KEY or a custom env var) but the skill metadata does not declare any required env vars. Treat this as a red flag — ask the publisher to add a declared primaryEnv and requires.env entries. - Verify the npm package: The SKILL.md instructs installing @youdotcom-oss/ai-sdk-plugin. Before running npm install, verify the package owner, inspect the package source (or its GitHub repo), and check for suspicious postinstall scripts or unexpected permissions. Prefer installing from trusted, verifiable sources. - Supply-chain risk: Because the skill relies on a third‑party package you will install locally, consider running the install in a controlled environment (CI, container) and review the package contents. - API key handling: Never paste your private API key into a UI — set it as an environment variable in your deployment environment. Confirm the least-privilege scope for the key on the You.com platform and rotate/regenerate if needed. - Ask the publisher: Request that they update the registry metadata to list YDC_API_KEY (or allow specifying primaryEnv) and provide links to the package repository/homepage so you can audit the code. If you need higher assurance, ask the publisher for the package repository link and a cryptographic provenance (e.g., GitHub repo + npm package match) and consider a quick code review of the package before installing.

Integrate AI SDK with You.com Tools

Interactive workflow to add You.com tools to your Vercel AI SDK application using @youdotcom-oss/ai-sdk-plugin.

Workflow

1. Ask: Package Manager

   • Which package manager? (npm, bun, yarn, pnpm)
   • Install package using their choice:

     npm install @youdotcom-oss/ai-sdk-plugin
     # or bun add @youdotcom-oss/ai-sdk-plugin
     # or yarn add @youdotcom-oss/ai-sdk-plugin
     # or pnpm add @youdotcom-oss/ai-sdk-plugin
     

2. Ask: Environment Variable Name

   • Using standard YDC_API_KEY?
   • Or custom name? (if custom, get the name)
   • Have they set it in their environment?
   • If NO: Guide them to get key from https://you.com/platform/api-keys

3. Ask: Which AI SDK Functions?

   • Do they use generateText()?
   • Do they use streamText()?
   • Both?

4. Ask: Existing Files or New Files?

   • EXISTING: Ask which file(s) to edit
   • NEW: Ask where to create file(s) and what to name them

5. For Each File, Ask:

   • Which tools to add?
     • youSearch (web search)
     • youExpress (AI agent)
     • youContents (content extraction)
     • Multiple? (which combination?)
   • Using generateText() or streamText() in this file?
   • Which AI provider model? (to determine if stopWhen needed)

6. Reference Integration Examples

   See "Integration Examples" section below for complete code patterns:

   • generateText() - Basic text generation with tools
   • streamText() - Streaming responses with web frameworks (Next.js, Express, React)

7. Update/Create Files

   For each file:

   • Reference integration examples (generateText or streamText based on their answer)
   • Add import for selected tools
   • If EXISTING file: Find their generateText/streamText call and add tools object
   • If NEW file: Create file with example structure
   • Tool invocation pattern based on env var name:
     • Standard YDC_API_KEY: youSearch()
     • Custom name: youSearch({ apiKey: process.env.CUSTOM_NAME })
   • Add selected tools to tools object
   • If streamText + Anthropic: Add stopWhen parameter

Integration Examples

generateText() - Basic Text Generation

Environment Variables Setup:

import { anthropic } from '@ai-sdk/anthropic';
import { generateText } from 'ai';
import { youContents, youExpress, youSearch } from '@youdotcom-oss/ai-sdk-plugin';

// Reads YDC_API_KEY from environment automatically
const result = await generateText({
  model: anthropic('claude-sonnet-4-5-20250929'),
  tools: {
    search: youSearch(),
  },
  prompt: 'What are the latest developments in quantum computing?',
});

console.log(result.text);

Multiple Tools:

const result = await generateText({
  model: anthropic('claude-sonnet-4-5-20250929'),
  tools: {
    search: youSearch(),      // Web search with citations
    agent: youExpress(),      // AI answers with web context
    extract: youContents(),   // Content extraction from URLs
  },
  prompt: 'Research quantum computing and summarize the key papers',
});

Custom API Key:

const result = await generateText({
  model: anthropic('claude-sonnet-4-5-20250929'),
  tools: {
    search: youSearch({ apiKey: 'your-custom-key' }),
  },
  prompt: 'Your prompt here',
});

Complete Example:

import { anthropic } from '@ai-sdk/anthropic';
import { generateText } from 'ai';
import { youSearch } from '@youdotcom-oss/ai-sdk-plugin';

const main = async () => {
  try {
    const result = await generateText({
      model: anthropic('claude-sonnet-4-5-20250929'),
      tools: {
        search: youSearch(),
      },
      maxSteps: 5,
      prompt: 'What are the latest developments in quantum computing?',
    });

    console.log('Generated text:', result.text);
    console.log('\nTool calls:', result.steps.flatMap(s => s.toolCalls));
  } catch (error) {
    console.error('Error:', error);
    process.exit(1);
  }
};

main();

streamText() - Streaming Responses

Basic Streaming with stopWhen Pattern:

import { anthropic } from '@ai-sdk/anthropic';
import { streamText, type StepResult } from 'ai';
import { youSearch } from '@youdotcom-oss/ai-sdk-plugin';

// CRITICAL: Always use stopWhen for Anthropic streaming
// Anthropic's SDK requires explicit stop conditions
const stepCountIs = (n: number) => (stepResult: StepResult<any>) =>
  stepResult.stepNumber >= n;

const result = streamText({
  model: anthropic('claude-sonnet-4-5-20250929'),
  tools: { search: youSearch() },
  stopWhen: stepCountIs(3),  // Required for Anthropic
  prompt: 'What are the latest AI developments?',
});

// Consume stream
for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Next.js Integration (App Router):

// app/api/chat/route.ts
import { anthropic } from '@ai-sdk/anthropic';
import { streamText, type StepResult } from 'ai';
import { youSearch } from '@youdotcom-oss/ai-sdk-plugin';

const stepCountIs = (n: number) => (stepResult: StepResult<any>) =>
  stepResult.stepNumber >= n;

export async function POST(req: Request) {
  const { prompt } = await req.json();

  const result = streamText({
    model: anthropic('claude-sonnet-4-5-20250929'),
    tools: { search: youSearch() },
    stopWhen: stepCountIs(5),
    prompt,
  });

  return result.toDataStreamResponse();
}

Express.js Integration:

// server.ts
import express from 'express';
import { anthropic } from '@ai-sdk/anthropic';
import { streamText, type StepResult } from 'ai';
import { youSearch } from '@youdotcom-oss/ai-sdk-plugin';

const app = express();
app.use(express.json());

const stepCountIs = (n: number) => (stepResult: StepResult<any>) =>
  stepResult.stepNumber >= n;

app.post('/api/chat', async (req, res) => {
  const { prompt } = req.body;

  const result = streamText({
    model: anthropic('claude-sonnet-4-5-20250929'),
    tools: { search: youSearch() },
    stopWhen: stepCountIs(5),
    prompt,
  });

  res.setHeader('Content-Type', 'text/plain; charset=utf-8');
  res.setHeader('Transfer-Encoding', 'chunked');

  for await (const chunk of result.textStream) {
    res.write(chunk);
  }

  res.end();
});

app.listen(3000);

React Client (with Next.js):

// components/Chat.tsx
'use client';

import { useChat } from 'ai/react';

export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit } = useChat({
    api: '/api/chat',
  });

  return (
    <div>
      {messages.map(m => (
        <div key={m.id}>
          <strong>{m.role}:</strong> {m.content}
        </div>
      ))}

      <form onSubmit={handleSubmit}>
        <input value={input} onChange={handleInputChange} />
        <button type="submit">Send</button>
      </form>
    </div>
  );
}

Complete Streaming Example:

import { anthropic } from '@ai-sdk/anthropic';
import { streamText, type StepResult } from 'ai';
import { youSearch } from '@youdotcom-oss/ai-sdk-plugin';

const stepCountIs = (n: number) => (stepResult: StepResult<any>) =>
  stepResult.stepNumber >= n;

const main = async () => {
  try {
    const result = streamText({
      model: anthropic('claude-sonnet-4-5-20250929'),
      tools: {
        search: youSearch(),
      },
      stopWhen: stepCountIs(3),
      prompt: 'What are the latest AI developments?',
    });

    // Stream to stdout
    console.log('Streaming response:\n');
    for await (const chunk of result.textStream) {
      process.stdout.write(chunk);
    }
    console.log('\n\nDone!');
  } catch (error) {
    console.error('Error:', error);
    process.exit(1);
  }
};

main();

Tool Invocation Patterns

Based on env var name from step 2:

Standard YDC_API_KEY:

import { youSearch } from '@youdotcom-oss/ai-sdk-plugin';

tools: {
  search: youSearch(),
}

Custom env var:

import { youSearch } from '@youdotcom-oss/ai-sdk-plugin';

const apiKey = process.env.THEIR_CUSTOM_NAME;

tools: {
  search: youSearch({ apiKey }),
}

Multiple tools with standard env var:

import { youSearch, youExpress, youContents } from '@youdotcom-oss/ai-sdk-plugin';

tools: {
  search: youSearch(),
  agent: youExpress(),
  extract: youContents(),
}

Multiple tools with custom env var:

import { youSearch, youExpress, youContents } from '@youdotcom-oss/ai-sdk-plugin';

const apiKey = process.env.THEIR_CUSTOM_NAME;

tools: {
  search: youSearch({ apiKey }),
  agent: youExpress({ apiKey }),
  extract: youContents({ apiKey }),
}

Available Tools

youSearch

Web and news search - model determines parameters (query, count, country, etc.)

youExpress

AI agent with web context - model determines parameters (input, tools)

youContents

Web page content extraction - model determines parameters (urls, format)

Key Integration Patterns

The examples above demonstrate:

• Import statements (AI SDK + provider + You.com tools)
• Env var validation (optional for new files)
• Tool configuration based on env var
• generateText/streamText usage with tools
• Result handling (especially textStream destructuring for streamText)
• Anthropic streaming pattern (stopWhen: stepCountIs(3))
• Web framework integration (Next.js, Express, React)

Implementation Checklist

For each file being updated/created:

• Import added for selected tools
• If custom env var: Variable declared with correct name
• tools object added to generateText/streamText
• Each selected tool invoked correctly:
  • Standard env: toolName()
  • Custom env: toolName({ apiKey })
• If streamText: Destructured const { textStream } = ...
• If Anthropic + streamText: Added stopWhen: stepCountIs(3)

Global checklist:

• Package installed with their package manager
• Env var set in their environment
• All files updated/created
• Ready to test

Common Issues

Issue: "Cannot find module @youdotcom-oss/ai-sdk-plugin" Fix: Install with their package manager

Issue: "YDC_API_KEY (or custom name) environment variable is required" Fix: Set in their environment (get key: https://you.com/platform/api-keys)

Issue: "Tool execution fails with 401" Fix: Verify API key is valid

Issue: "Incomplete or missing response" Fix: If using streamText, increase the step count. Start with 3 and iterate up as needed (see README troubleshooting)

Issue: "textStream is not iterable" Fix: Destructure: const { textStream } = streamText(...)

Issue: "Custom env var not working" Fix: Pass to each tool: youSearch({ apiKey })

Advanced: Tool Development Patterns

For developers creating custom AI SDK tools or contributing to @youdotcom-oss/ai-sdk-plugin:

Tool Function Structure

Each tool function follows this pattern:

export const youToolName = (config: YouToolsConfig = {}) => {
  const apiKey = config.apiKey ?? process.env.YDC_API_KEY;

  return tool({
    description: 'Tool description for AI model',
    inputSchema: ZodSchema,
    execute: async (params) => {
      if (!apiKey) {
        throw new Error('YDC_API_KEY is required');
      }

      const response = await callApiUtility({
        params,
        YDC_API_KEY: apiKey,
        getUserAgent,
      });

      // Return raw API response for maximum flexibility
      return response;
    },
  });
};

Input Schemas Enable Smart Queries

Always use schemas from @youdotcom-oss/mcp:

// ✅ Import from @youdotcom-oss/mcp
import { SearchQuerySchema } from '@youdotcom-oss/mcp';

export const youSearch = (config: YouToolsConfig = {}) => {
  return tool({
    description: '...',
    inputSchema: SearchQuerySchema,  // Enables AI to use all search parameters
    execute: async (params) => { ... },
  });
};

// ❌ Don't duplicate or simplify schemas
const MySearchSchema = z.object({ query: z.string() });  // Missing filters!

Why this matters:

• Rich schemas enable AI to use advanced query parameters (filters, freshness, country, etc.)
• AI can construct more intelligent queries based on user intent
• Prevents duplicating schema definitions across packages
• Ensures consistency with MCP server schemas

API Key Handling

Always provide environment variable fallback and validate before API calls:

// ✅ Automatic environment variable fallback
const apiKey = config.apiKey ?? process.env.YDC_API_KEY;

// ✅ Check API key in execute function
execute: async (params) => {
  if (!apiKey) {
    throw new Error('YDC_API_KEY is required');
  }
  const response = await callApi(...);
}

Response Format

Always return raw API response for maximum flexibility:

// ✅ Return raw API response
execute: async (params) => {
  const response = await fetchSearchResults({
    searchQuery: params,
    YDC_API_KEY: apiKey,
    getUserAgent,
  });

  return response;  // Raw response for maximum flexibility
}

// ❌ Don't format or transform responses
return {
  text: formatResponse(response),
  data: response,
};

Why raw responses?

• Maximum flexibility for AI SDK to process results
• No information loss from formatting
• AI SDK handles presentation layer
• Easier to debug (see actual API response)

Tool Descriptions

Write descriptions that guide AI behavior:

// ✅ Clear guidance for AI model
description: 'Search the web for current information, news, articles, and content using You.com. Returns web results with snippets and news articles. Use this when you need up-to-date information or facts from the internet.'

// ❌ Too brief
description: 'Search the web'

Additional Resources

• Package README: https://github.com/youdotcom-oss/dx-toolkit/tree/main/packages/ai-sdk-plugin
• Vercel AI SDK Docs: https://ai-sdk.dev/docs
• You.com API: https://you.com/platform/api-keys