How to Use the MOBIDI MCP in OpenAI Agents SDK

Q: How do I configure MOBIDI with openai-agents-sdk?

Install openai-agents via pip and initialize the MCP connection using MCPServerStreamableHttp. Pass the endpoint URL directly into your agent constructor to auto-discover the campaign management tools.

Q: Can openai-agents-sdk run MOBIDI reports asynchronously?

Yes, you can run executereport asynchronously within the SDK's runtime loop. This prevents your agent from blocking while waiting for large mobile ad performance datasets to compile.

Q: What tools does this MCP Server provide?

It exposes 12 distinct tools including createrecord, updaterecord, and getservices to control your mobile ad operations. Your agent can query, edit, or delete records in real time.

Run production OpenAI Agents SDK workflows that manage MOBIDI mobile ad campaigns and trigger real-time bidding updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MOBIDI MCP to OpenAI Agents SDK

Create your Vinkius account to connect MOBIDI 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 MOBIDI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run MOBIDI reports directly inside OpenAI Agents SDK

Your agent can spin up complex queries using `execute_report` to pull immediate install numbers. It takes the output, processes the numbers, and uses `get_report` to verify the campaign performance against your target CPI. This gives your OpenAI Agents SDK system the exact data it needs to shift budgets between active ad groups. You don't have to write custom polling loops because the agent handles the raw JSON payloads natively.

Safe campaign updates with built-in guardrails

Prevent your agent from going rogue on bidding parameters by wrapping `update_record` with native OpenAI safety limits. The SDK checks the proposed ad spend before committing the edit to the MOBIDI database. If the agent attempts to scale a budget too quickly, your guardrails catch it before `update_record` runs. You get programmatic control over live mobile campaigns without worrying about runaway API spending.

Auto-discover tools for fast deployment

Your OpenAI Agents SDK agent can pull your full database layout using `list_records` without manual configuration. Your setup code doesn't need manual tool mapping for campaign utilities to work. The SDK reads the server configuration, maps the schema, and lets the agent start querying mobile ad records immediately. It keeps your codebase clean and reduces configuration overhead.

Setup guide

Set up MOBIDI 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 MOBIDI tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate MOBIDI 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="MOBIDI Agent",
            instructions="You have access to MOBIDI 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 MOBIDI. 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 MOBIDI 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 MOBIDI MCP in OpenAI Agents SDK

Install `openai-agents` via pip and initialize the MCP connection using `MCPServerStreamableHttp`. Pass the endpoint URL directly into your agent constructor to auto-discover the campaign management tools.

Yes, you can run `execute_report` asynchronously within the SDK's runtime loop. This prevents your agent from blocking while waiting for large mobile ad performance datasets to compile.

The SDK relies on your upstream API limits, but you can use `get_record_count` to throttle agent requests before they trigger a block. This keeps your automated bidding workflows running smoothly.

It exposes 12 distinct tools including `create_record`, `update_record`, and `get_services` to control your mobile ad operations. Your agent can query, edit, or delete records in real time.

Your bidding budgets and campaign records remain inside a zero-trust V8 sandbox through this MCP connection. Authentication is handled via a single secure endpoint token, meaning no raw credential storage happens on external servers.

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