How to Use the Nimbleway MCP in OpenAI Agents SDK

Q: How do I configure Nimbleway with OpenAI Agents SDK?

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your Nimbleway endpoint and pass it to the agent constructor as an MCP server. The framework auto-discovers all ten tools.

Q: Can the OpenAI Agents SDK trigger Nimbleway web searches?

Yes. The agent calls the searchweb tool with a specific query. It parses the results and decides which URLs to scrape next.

Q: How does Nimbleway handle rate limits in OpenAI Agents SDK?

Your agent checks limits using the getaccountusage tool. If bandwidth runs low, your OpenAI guardrails can pause execution automatically.

Give your OpenAI Agents SDK production-grade web scraping and search tools via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimbleway MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Web Scraping for OpenAI Agents SDK

The `extract_markdown` and `extract_html` tools pull clean text and raw DOM data directly into your agent context. You run a `search_web` query to find relevant targets, and the agent reads the pages immediately. This MCP Server runs with OpenAI's built-in guardrails. Your system validates the extraction parameters before hitting the target site. You trace every HTTP request through the OpenAI dashboard to ensure the agent stays on task.

Manage Scraping Pipelines

The `list_pipelines` and `get_pipeline` tools let your agents read static scraping configurations through the MCP protocol. When a process starts, the `list_jobs` and `get_job` tools report exact execution status back to the agent. Complex extraction tasks require specialized workers. You build one agent to queue the jobs and another to poll the results. Handoffs happen naturally when the job finishes.

Monitor Proxy Health

The `list_proxies` tool returns your active routing configurations. Your agent calls `get_account_usage` and `get_me` to check bandwidth limits before starting a massive crawl. Production agents need hard boundaries. If the usage spikes, the agent stops making requests. You define the safety constraints, and the tools respect them.

Setup guide

Set up Nimbleway 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 Nimbleway tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the `openai-agents` package via pip. Create an `MCPServerStreamableHttp` instance with your Nimbleway endpoint and pass it to the agent constructor as an MCP server. The framework auto-discovers all ten tools.

Yes. The agent calls the `search_web` tool with a specific query. It parses the results and decides which URLs to scrape next.

Your agent checks limits using the `get_account_usage` tool. If bandwidth runs low, your OpenAI guardrails can pause execution automatically.

The framework uses an async context manager. This allows your agent to handle multiple long-running web requests concurrently.

Vinkius processes your target URLs, raw HTML payloads, and proxy configurations in a V8 Isolate Sandbox. The environment is ephemeral and destroys the memory state immediately after the request finishes. Zero data persists on our infrastructure.

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