OpenAI Agents SDK

import os
from agents import Agent, Runner
from agents.mcp import MCPServerSse

# Connect to Datashift MCP server
datashift_server = MCPServerSse(
    url="https://mcp.datashift.io/sse",
    headers={
        "Authorization": f"Bearer {os.environ['DATASHIFT_ACCESS_TOKEN']}"
    }
)

# Create agent with access to Datashift MCP tools
agent = Agent(
    name="Customer Support Agent",
    instructions="""You are a customer support agent that helps customers.

When you need to take important actions like sending emails, updating records,
or making changes that could affect customers, use the submit_task tool from
the datashift MCP server to get human approval first.

For example, before sending any email:
1. Call submit_task with queue_key="outbound-communications"
2. Include the email details in the data field
3. Wait for the task to be reviewed
4. Read the task resource to check if it was approved
5. Only proceed if approved

You decide when human review is needed based on the sensitivity of the action.""",
    mcp_servers=[datashift_server],
)

# Run the agent
runner = Runner()
response = runner.run(
    agent,
    messages=[{
        "role": "user",
        "content": "Send a follow-up email to john@example.com thanking them for their purchase"
    }]
)

print(response.final_output)

agent = Agent(
    name="Data Processing Agent",
    instructions="""You process and enrich customer data.

When you encounter situations where you're uncertain about data quality
or need human verification, use the Datashift MCP tools:

- submit_task: Submit data for human review
- list_queues: See available review queues
- get_queue_config: Check queue settings

Use queue_key="data-verification" for data quality checks.
Use queue_key="customer-updates" for customer record changes.

You decide when to request review based on:
- Data confidence level
- Potential customer impact
- Regulatory requirements

After submitting a task, the MCP server will notify you when the review
is complete. Read the task resource to get the reviewer's decision.""",
    mcp_servers=[datashift_server],
)

from agents import Agent, handoff

# Agent that handles human review via Datashift
review_agent = Agent(
    name="Human Review Coordinator",
    instructions="""You coordinate human reviews via Datashift.

When another agent hands off to you, submit the task for review
using the submit_task MCP tool. Monitor for completion and
return the reviewer's decision.""",
    mcp_servers=[datashift_server],
)

# Main agent that can escalate to human review
main_agent = Agent(
    name="Sales Agent",
    instructions="""You handle sales inquiries.

For high-value deals over $10,000 or complex negotiations,
hand off to the Human Review Coordinator for approval before
finalizing any commitments.""",
    handoffs=[handoff(review_agent)],
)