How to Use the Bland AI MCP in OpenAI Agents SDK

Q: Does the Bland AI integration support multi-agent handoffs in OpenAI Agents SDK?

Yes, you can dedicate one agent to analyze call logs using gettranscript and another to trigger new actions with sendcall. The SDK handles the context transfer between them.

Q: How does caching improve tool discovery performance?

Setting cacheToolsList=True stops the SDK from querying the Vinkius gateway for the tool schema on every single turn. This reduces latency when your agent decides to list active calls.

Trigger automated phone calls and pull transcripts directly inside your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bland AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Bland AI to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Bland AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run automated phone agents via OpenAI Agents SDK

`send_call` triggers an outbound phone call using Bland AI's voice network directly from your Python agent. Your agent uses this tool to initiate conversations, passing custom prompts and structured pathways to handle complex customer interactions over the wire. Configure this setup by adding the MCP server to your `Agent(mcp_servers=[server])` list. The server registers all available tools automatically, allowing your specialized agents to hand off call tasks to each other while OpenAI's dashboard tracks every execution.

Stop active calls and audit transcripts on the fly

`stop_call` terminates an active or scheduled phone call instantly when your system detects a conflict or a user request to cancel. If you need to review what happened during a completed conversation, `get_transcript` pulls the full text log directly into your runner's context. This setup relies on the MCP Server to maintain a persistent connection between your codebase and the Vinkius gateway. By setting `cacheToolsList=True` in your parameters, you avoid unnecessary network roundtrips when checking agent states or listing recent calls.

Dynamically switch voices and conversational pathways

`list_voices` returns the complete set of available vocal profiles so your agent can select the right tone before placing a call. Once you choose a voice, `get_pathway` retrieves the exact decision tree your phone agent will follow during the live conversation. This MCP Server lets your multi-agent architecture match caller profiles to specific agent behaviors. The OpenAI framework handles the routing, ensuring that only validated parameters pass to the underlying API endpoints.

Setup guide

Set up Bland AI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Bland AI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Bland AI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Bland AI tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Bland AI Agent",
            instructions="You have access to Bland AI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Bland AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Bland AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Bland AI MCP in OpenAI Agents SDK

Install the package using pip, then initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when instantiating your `Agent` object.

Yes, you can control tool access using the framework's native guardrails. By wrapping the agent configuration, you prevent unauthorized execution of tools like `send_call` or `stop_call`.

Yes, you can dedicate one agent to analyze call logs using `get_transcript` and another to trigger new actions with `send_call`. The SDK handles the context transfer between them.

Setting `cacheToolsList=True` stops the SDK from querying the Vinkius gateway for the tool schema on every single turn. This reduces latency when your agent decides to list active calls.

Your phone transcripts and call metadata route directly through Vinkius's secure, ephemeral V8 sandboxes. No call logs are stored on the hosting platform, keeping your voice data isolated and private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript