Integrate OpenAI Agents SDK with You.com MCP server

Integrate OpenAI Agents SDK with You.com MCP server - Hosted and Streamable HTTP support for Python and TypeScript. Use when developer mentions OpenAI Agents SDK, OpenAI agents, or integrating OpenAI with MCP.

Security Scan

The skill's instructions and requirements are coherent for integrating the OpenAI Agents SDK with You.com's MCP; the main issue is a metadata mismatch where the SKILL.md asks for API keys but the registry metadata declares no required env vars.

Purpose & Capability

Name, description, and runtime instructions all describe integrating the OpenAI Agents SDK with You.com's MCP server. The recommended installs (pip/npm) and the code templates match the claimed purpose.

Instruction Scope

Instructions are limited to asking questions, installing the SDK packages, and creating/updating project files with MCP configuration. Templates include a 'require_approval': 'never' setting in one example which reduces manual approval for tool use — this is a configuration choice relevant to runtime safety and should be reviewed before use.

Install Mechanism

No install spec in the skill bundle (instruction-only). The SKILL.md suggests installing published packages via pip/npm (openai-agents/@openai/agents), which is expected and low-risk compared with arbitrary downloads.

Credentials

The skill's metadata declares no required environment variables, but the SKILL.md and templates explicitly require YDC_API_KEY and OPENAI_API_KEY. Requesting those two keys is proportionate to the stated integration, but the metadata mismatch is an incoherence that should be corrected/clarified before trusting the skill.

Persistence & Privilege

Skill is not always-enabled and uses normal agent invocation. Templates configure agent/tool behavior (e.g., 'require_approval': 'never') which affects runtime autonomy — this is not a skill-level permission but it changes how the integrated agent will behave and should be audited.

Assessment

This skill appears to do what it says: it provides templates and step-by-step guidance to wire the OpenAI Agents SDK to You.com's MCP and asks for the expected API keys. Before installing or using: (1) Note the metadata mismatch — the registry says no env vars required but the templates require YDC_API_KEY and OPENAI_API_KEY; don't paste keys into files or share them in chat. (2) Review the templates locally before running; pay attention to the 'require_approval': 'never' setting (it lets the agent call tools without extra prompts). (3) Install packages from the official registries (PyPI/npm) and verify package names and maintainers. (4) Run first in a development environment with least-privilege API keys, and rotate keys if you later decide they may have been exposed. (5) If you need the registry metadata corrected (so required env vars are declared), ask the skill author to update it; metadata should match the runtime instructions.

Integrate OpenAI Agents SDK with You.com MCP

Interactive workflow to set up OpenAI Agents SDK with You.com's MCP server.

Workflow

1. Ask: Language Choice

   • Python or TypeScript?

2. Ask: MCP Configuration Type

   • Hosted MCP (OpenAI-managed with server URL): Recommended for simplicity
   • Streamable HTTP (Self-managed connection): For custom infrastructure

3. Install Package

   • Python: pip install openai-agents
   • TypeScript: npm install @openai/agents

4. Ask: Environment Variables

   For Both Modes:

   • YDC_API_KEY (You.com API key for Bearer token)
   • OPENAI_API_KEY (OpenAI API key)

   Have they set them?

   • If NO: Guide to get keys:
     • YDC_API_KEY: https://you.com/platform/api-keys
     • OPENAI_API_KEY: https://platform.openai.com/api-keys

5. Ask: File Location

   • NEW file: Ask where to create and what to name
   • EXISTING file: Ask which file to integrate into (add MCP config)

6. Create/Update File

   For NEW files:

   • Use the complete template code from the "Complete Templates" section below
   • User can run immediately with their API keys set

   For EXISTING files:

   • Add MCP server configuration to their existing code

   Hosted MCP configuration block (Python):

   from agents import Agent, Runner
   from agents.mcp import HostedMCPTool
   
   # Validate: ydc_api_key = os.getenv("YDC_API_KEY")
   agent = Agent(
       name="Assistant",
       instructions="Use You.com tools to answer questions.",
       tools=[
           HostedMCPTool(
               tool_config={
                   "type": "mcp",
                   "server_label": "ydc",
                   "server_url": "https://api.you.com/mcp",
                   "headers": {
                       "Authorization": f"Bearer {ydc_api_key}"
                   },
                   "require_approval": "never",
               }
           )
       ],
   )
   

   Hosted MCP configuration block (TypeScript):

   import { Agent, hostedMcpTool } from '@openai/agents';
   
   // Validate: const ydcApiKey = process.env.YDC_API_KEY;
   const agent = new Agent({
     name: 'Assistant',
     instructions: 'Use You.com tools to answer questions.',
     tools: [
       hostedMcpTool({
        serverLabel: 'ydc',
         serverUrl: 'https://api.you.com/mcp',
         headers: {
           Authorization: `Bearer ${ydcApiKey}`,
         },
       }),
     ],
   });
   

   Streamable HTTP configuration block (Python):

   from agents import Agent, Runner
   from agents.mcp import MCPServerStreamableHttp
   
   # Validate: ydc_api_key = os.getenv("YDC_API_KEY")
   async with MCPServerStreamableHttp(
       name="You.com MCP Server",
       params={
           "url": "https://api.you.com/mcp",
           "headers": {"Authorization": f"Bearer {ydc_api_key}"},
           "timeout": 10,
       },
       cache_tools_list=True,
       max_retry_attempts=3,
   ) as server:
       agent = Agent(
           name="Assistant",
           instructions="Use You.com tools to answer questions.",
           mcp_servers=[server],
       )
   

   Streamable HTTP configuration block (TypeScript):

   import { Agent, MCPServerStreamableHttp } from '@openai/agents';
   
   // Validate: const ydcApiKey = process.env.YDC_API_KEY;
   const mcpServer = new MCPServerStreamableHttp({
     url: 'https://api.you.com/mcp',
     name: 'You.com MCP Server',
     requestInit: {
       headers: {
         Authorization: `Bearer ${ydcApiKey}`,
       },
     },
   });
   
   const agent = new Agent({
     name: 'Assistant',
     instructions: 'Use You.com tools to answer questions.',
     mcpServers: [mcpServer],
   });
   

Complete Templates

Use these complete templates for new files. Each template is ready to run with your API keys set.

Python Hosted MCP Template (Complete Example)

"""
OpenAI Agents SDK with You.com Hosted MCP
Python implementation with OpenAI-managed infrastructure
"""

import os
import asyncio
from agents import Agent, Runner
from agents.mcp import HostedMCPTool

# Validate environment variables
ydc_api_key = os.getenv("YDC_API_KEY")
openai_api_key = os.getenv("OPENAI_API_KEY")

if not ydc_api_key:
    raise ValueError(
        "YDC_API_KEY environment variable is required. "
        "Get your key at: https://you.com/platform/api-keys"
    )

if not openai_api_key:
    raise ValueError(
        "OPENAI_API_KEY environment variable is required. "
        "Get your key at: https://platform.openai.com/api-keys"
    )


async def main():
    """
    Example: Search for AI news using You.com hosted MCP tools
    """
    # Configure agent with hosted MCP tools
    agent = Agent(
        name="AI News Assistant",
        instructions="Use You.com tools to search for and answer questions about AI news.",
        tools=[
            HostedMCPTool(
                tool_config={
                    "type": "mcp",
                    "server_label": "ydc",
                    "server_url": "https://api.you.com/mcp",
                    "headers": {
                        "Authorization": f"Bearer {ydc_api_key}"
                    },
                    "require_approval": "never",
                }
            )
        ],
    )

    # Run agent with user query
    result = await Runner.run(
        agent,
        "Search for the latest AI news from this week"
    )

    print(result.final_output)


if __name__ == "__main__":
    asyncio.run(main())

Python Streamable HTTP Template (Complete Example)

"""
OpenAI Agents SDK with You.com Streamable HTTP MCP
Python implementation with self-managed connection
"""

import os
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

# Validate environment variables
ydc_api_key = os.getenv("YDC_API_KEY")
openai_api_key = os.getenv("OPENAI_API_KEY")

if not ydc_api_key:
    raise ValueError(
        "YDC_API_KEY environment variable is required. "
        "Get your key at: https://you.com/platform/api-keys"
    )

if not openai_api_key:
    raise ValueError(
        "OPENAI_API_KEY environment variable is required. "
        "Get your key at: https://platform.openai.com/api-keys"
    )


async def main():
    """
    Example: Search for AI news using You.com streamable HTTP MCP server
    """
    # Configure streamable HTTP MCP server
    async with MCPServerStreamableHttp(
        name="You.com MCP Server",
        params={
            "url": "https://api.you.com/mcp",
            "headers": {"Authorization": f"Bearer {ydc_api_key}"},
            "timeout": 10,
        },
        cache_tools_list=True,
        max_retry_attempts=3,
    ) as server:
        # Configure agent with MCP server
        agent = Agent(
            name="AI News Assistant",
            instructions="Use You.com tools to search for and answer questions about AI news.",
            mcp_servers=[server],
        )

        # Run agent with user query
        result = await Runner.run(
            agent,
            "Search for the latest AI news from this week"
        )

        print(result.final_output)


if __name__ == "__main__":
    asyncio.run(main())

TypeScript Hosted MCP Template (Complete Example)

/**
 * OpenAI Agents SDK with You.com Hosted MCP
 * TypeScript implementation with OpenAI-managed infrastructure
 */

import { Agent, run, hostedMcpTool } from '@openai/agents';

// Validate environment variables
const ydcApiKey = process.env.YDC_API_KEY;
const openaiApiKey = process.env.OPENAI_API_KEY;

if (!ydcApiKey) {
  throw new Error(
    'YDC_API_KEY environment variable is required. ' +
      'Get your key at: https://you.com/platform/api-keys'
  );
}

if (!openaiApiKey) {
  throw new Error(
    'OPENAI_API_KEY environment variable is required. ' +
      'Get your key at: https://platform.openai.com/api-keys'
  );
}

/**
 * Example: Search for AI news using You.com hosted MCP tools
 */
async function main() {
  // Configure agent with hosted MCP tools
  const agent = new Agent({
    name: 'AI News Assistant',
    instructions:
      'Use You.com tools to search for and answer questions about AI news.',
    tools: [
      hostedMcpTool({
        serverLabel: 'ydc',
        serverUrl: 'https://api.you.com/mcp',
        headers: {
          Authorization: `Bearer ${ydcApiKey}`,
        },
      }),
    ],
  });

  // Run agent with user query
  const result = await run(
    agent,
    'Search for the latest AI news from this week'
  );

  console.log(result.finalOutput);
}

main().catch(console.error);

TypeScript Streamable HTTP Template (Complete Example)

/**
 * OpenAI Agents SDK with You.com Streamable HTTP MCP
 * TypeScript implementation with self-managed connection
 */

import { Agent, run, MCPServerStreamableHttp } from '@openai/agents';

// Validate environment variables
const ydcApiKey = process.env.YDC_API_KEY;
const openaiApiKey = process.env.OPENAI_API_KEY;

if (!ydcApiKey) {
  throw new Error(
    'YDC_API_KEY environment variable is required. ' +
      'Get your key at: https://you.com/platform/api-keys'
  );
}

if (!openaiApiKey) {
  throw new Error(
    'OPENAI_API_KEY environment variable is required. ' +
      'Get your key at: https://platform.openai.com/api-keys'
  );
}

/**
 * Example: Search for AI news using You.com streamable HTTP MCP server
 */
async function main() {
  // Configure streamable HTTP MCP server
  const mcpServer = new MCPServerStreamableHttp({
    url: 'https://api.you.com/mcp',
    name: 'You.com MCP Server',
    requestInit: {
      headers: {
        Authorization: `Bearer ${ydcApiKey}`,
      },
    },
  });

  try {
    // Connect to MCP server
    await mcpServer.connect();

    // Configure agent with MCP server
    const agent = new Agent({
      name: 'AI News Assistant',
      instructions:
        'Use You.com tools to search for and answer questions about AI news.',
      mcpServers: [mcpServer],
    });

    // Run agent with user query
    const result = await run(
      agent,
      'Search for the latest AI news from this week'
    );

    console.log(result.finalOutput);
  } finally {
    // Clean up connection
    await mcpServer.close();
  }
}

main().catch(console.error);

MCP Configuration Types

Hosted MCP (Recommended)

What it is: OpenAI manages the MCP connection and tool routing through their Responses API.

Benefits:

• ✅ Simpler configuration (no connection management)
• ✅ OpenAI handles authentication and retries
• ✅ Lower latency (tools run in OpenAI infrastructure)
• ✅ Automatic tool discovery and listing
• ✅ No need to manage async context or cleanup

Use when:

• Building production applications
• Want minimal boilerplate code
• Need reliable tool execution
• Don't require custom transport layer

Configuration:

Python:

from agents.mcp import HostedMCPTool

tools=[
    HostedMCPTool(
        tool_config={
            "type": "mcp",
            "server_label": "ydc",
            "server_url": "https://api.you.com/mcp",
            "headers": {
                "Authorization": f"Bearer {os.environ['YDC_API_KEY']}"
            },
            "require_approval": "never",
        }
    )
]

TypeScript:

import { hostedMcpTool } from '@openai/agents';

tools: [
  hostedMcpTool({
    serverLabel: 'ydc',
    serverUrl: 'https://api.you.com/mcp',
    headers: {
      Authorization: `Bearer ${process.env.YDC_API_KEY}`,
    },
  }),
]

Streamable HTTP MCP

What it is: You manage the MCP connection and transport layer yourself.

Benefits:

• ✅ Full control over network connection
• ✅ Custom infrastructure integration
• ✅ Can add custom headers, timeouts, retry logic
• ✅ Run MCP server in your own environment
• ✅ Better for testing and development

Use when:

• Need custom transport configuration
• Running MCP server in your infrastructure
• Require specific networking setup
• Development and testing scenarios

Configuration:

Python:

from agents.mcp import MCPServerStreamableHttp

async with MCPServerStreamableHttp(
    name="You.com MCP Server",
    params={
        "url": "https://api.you.com/mcp",
        "headers": {"Authorization": f"Bearer {os.environ['YDC_API_KEY']}"},
        "timeout": 10,
    },
    cache_tools_list=True,
    max_retry_attempts=3,
) as server:
    agent = Agent(mcp_servers=[server])

TypeScript:

import { MCPServerStreamableHttp } from '@openai/agents';

const mcpServer = new MCPServerStreamableHttp({
  url: 'https://api.you.com/mcp',
  name: 'You.com MCP Server',
  requestInit: {
    headers: {
      Authorization: `Bearer ${process.env.YDC_API_KEY}`,
    },
  },
});

await mcpServer.connect();
try {
  const agent = new Agent({ mcpServers: [mcpServer] });
  // Use agent
} finally {
  await mcpServer.close();
}

Available You.com Tools

After configuration, agents can discover and use:

• mcp__ydc__you_search - Web and news search
• mcp__ydc__you_express - AI-powered answers with web context
• mcp__ydc__you_contents - Web page content extraction

Environment Variables

Both API keys are required for both configuration modes:

# Add to your .env file or shell profile
export YDC_API_KEY="your-you-api-key-here"
export OPENAI_API_KEY="your-openai-api-key-here"

Get your API keys:

• You.com: https://you.com/platform/api-keys
• OpenAI: https://platform.openai.com/api-keys

Validation Checklist

Before completing:

• Package installed: openai-agents (Python) or @openai/agents (TypeScript)
• Environment variables set: YDC_API_KEY and OPENAI_API_KEY
• Template copied or configuration added to existing file
• MCP configuration type chosen (Hosted or Streamable HTTP)
• Authorization headers configured with Bearer token
• File is executable (Python) or can be compiled (TypeScript)
• Ready to test with example query

Testing Your Integration

Python:

python your-file.py

TypeScript:

# With tsx (recommended for quick testing)
npx tsx your-file.ts

# Or compile and run
tsc your-file.ts && node your-file.js

Common Issues

<details> <summary><strong>Cannot find module @openai/agents</strong></summary>

Install the package:

# NPM
npm install @openai/agents

# Bun
bun add @openai/agents

# Yarn
yarn add @openai/agents

# pnpm
pnpm add @openai/agents

</details> <details> <summary><strong>YDC_API_KEY environment variable is required</strong></summary>

Set your You.com API key:

export YDC_API_KEY="your-api-key-here"

Get your key at: https://you.com/platform/api-keys

</details> <details> <summary><strong>OPENAI_API_KEY environment variable is required</strong></summary>

Set your OpenAI API key:

export OPENAI_API_KEY="your-api-key-here"

Get your key at: https://platform.openai.com/api-keys

</details> <details> <summary><strong>MCP connection fails with 401 Unauthorized</strong></summary>

Verify your YDC_API_KEY is valid:

1. Check the key at https://you.com/platform/api-keys
2. Ensure no extra spaces or quotes in the environment variable
3. Verify the Authorization header format: Bearer ${YDC_API_KEY}

</details> <details> <summary><strong>Tools not available or not being called</strong></summary>

For Both Modes:

• Ensure server_url: "https://api.you.com/mcp" is correct
• Verify Authorization header includes Bearer prefix
• Check YDC_API_KEY environment variable is set
• Confirm require_approval is set to "never" for automatic execution

For Streamable HTTP specifically:

• Ensure MCP server is connected before creating agent
• Verify connection was successful before running agent

</details> <details> <summary><strong>Connection timeout or network errors</strong></summary>

For Streamable HTTP only:

Increase timeout or retry attempts:

Python:

async with MCPServerStreamableHttp(
    params={
        "url": "https://api.you.com/mcp",
        "headers": {"Authorization": f"Bearer {os.environ['YDC_API_KEY']}"},
        "timeout": 30,  # Increased timeout
    },
    max_retry_attempts=5,  # More retries
) as server:
    # ...

TypeScript:

const mcpServer = new MCPServerStreamableHttp({
  url: 'https://api.you.com/mcp',
  requestInit: {
    headers: { Authorization: `Bearer ${process.env.YDC_API_KEY}` },
    // Add custom timeout via fetch options
  },
});

</details>

Additional Resources

• OpenAI Agents SDK (Python): https://openai.github.io/openai-agents-python/
• OpenAI Agents SDK (TypeScript): https://openai.github.io/openai-agents-js/
• MCP Configuration (Python): https://openai.github.io/openai-agents-python/mcp/
• MCP Configuration (TypeScript): https://openai.github.io/openai-agents-js/guides/mcp/
• You.com MCP Server: https://documentation.you.com/developer-resources/mcp-server
• API Keys:
  • You.com: https://you.com/platform/api-keys
  • OpenAI: https://platform.openai.com/api-keys