# OpenAI Agents SDK Setup

> Connect OpenAI Agents SDK to graph8 via MCP using MCPServerStreamableHttp

Source: https://docs.graph8.com/developers/openai-sdk-setup/

Connect the OpenAI Agents SDK to graph8's MCP server. The Agents SDK ships with native MCP support, so a graph8 connection is a single `MCPServerStreamableHttp` call away.

> **Tip:**
> Try the developer tier free - 1,000 credits, no card required. [Get started](https://auth.graph8.com/en/signup).

## Prerequisites

- Python 3.10+
- `openai-agents` SDK with the MCP extra

```bash
pip install 'openai-agents[mcp]'
```

## Hosted MCP (remote OAuth)

```python
import asyncio
import os

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

async def main() -> None:
    async with MCPServerStreamableHttp(
        name="graph8",
        params={"url": "https://be.graph8.com/mcp/"},
    ) as server:
        agent = Agent(
            name="ProspectFinder",
            instructions=(
                "You find prospects for SaaS GTM teams. Use g8_find_contacts to "
                "preview. Never call g8_build_contact_list, g8_enrich_contacts, "
                "or g8_add_to_sequence without explicit user confirmation."
            ),
            mcp_servers=[server],
            model="gpt-4o",
        )

        result = await Runner.run(
            agent,
            "Find 10 VP Engineering at Series B SaaS in the US. "
            "Return name, company, title, and linkedin URL.",
        )
        print(result.final_output)

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

The first run prompts for OAuth in a browser. The SDK caches the token.

## Self-hosted MCP (stdio)

```python
import os

from agents.mcp import MCPServerStdio

server = MCPServerStdio(
    name="graph8",
    params={
        "command": "uvx",
        "args": ["g8-mcp-server"],
        "env": {
            "G8_API_KEY": os.environ["G8_API_KEY"],
            "G8_MCP_MODE": "gtm",
        },
    },
)
```

## Worked example: one-shot prospect list

```python
import asyncio

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

async def build_prospect_list() -> None:
    async with MCPServerStreamableHttp(
        name="graph8",
        params={"url": "https://be.graph8.com/mcp/"},
    ) as server:
        agent = Agent(
            name="GTMAgent",
            instructions=(
                "Step 1: g8_find_contacts to preview 50 VP Eng at Series B SaaS.\n"
                "Step 2: Pick the top 25 by signal score. Ask the user to confirm.\n"
                "Step 3: g8_build_contact_list named 'Series B SaaS VP Eng'.\n"
                "Step 4: g8_list_sequences to find 'New SaaS Outreach'.\n"
                "Step 5: g8_add_to_sequence after confirmation.\n"
            ),
            mcp_servers=[server],
            model="gpt-4o",
        )
        result = await Runner.run(agent, "Run the full prospect-to-sequence flow.")
        print(result.final_output)

asyncio.run(build_prospect_list())
```

The Agents SDK's `Runner` handles tool-call loops automatically. graph8's confirmation rule for credit-charging tools surfaces as natural-language prompts to the user before any save.

## Related

- [MCP Server overview](https://docs.graph8.com/developers/mcp/)
- [MCP Tool Reference](https://docs.graph8.com/developers/mcp-tools/)
- [MCP FAQ](https://docs.graph8.com/developers/mcp-faq/)
- [End-to-end examples](https://docs.graph8.com/developers/mcp-examples/)