How to Use the Firecrawl MCP in OpenAI Agents SDK

Q: What happens if a crawl job takes too long?

The crawlsite tool returns an async job ID immediately. Your agent can poll the status or execute other tasks instead of hanging the connection.

Turn web content into clean Markdown for your OpenAI Agents SDK pipelines using raw HTTP streaming.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firecrawl MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Clean web extraction for OpenAI Agents SDK

The `scrape_page` tool converts raw HTML into clean, LLM-ready Markdown while handling annoying cookiewalls and anti-bot systems behind the scenes. Your OpenAI agent gets only the actual content, bypassing the junk code that blows up token costs. Under the hood, this MCP Server integrates directly into the agent's tool declaration array. It strips out scripts, ads, and navigation blocks so your LLM gets pure text on the first try.

Mapping site architecture with this MCP Server

The `map_site` tool returns a clean list of URLs from a target domain, giving your agent a full blueprint of the site's layout before it attempts to read individual pages. This prevents your script from wasting compute on irrelevant links. When your OpenAI agent needs to discover where documentation lives, this tool feeds it the sitemap instantly. It avoids blind crawling, saving API calls and keeping your token budget under control.

Deep recursive web crawling

The `crawl_site` tool kicks off an asynchronous process to scrape every page of a target domain and convert the entire site into structured Markdown. You get a job ID immediately, allowing your agent to track progress while executing other tasks. This tool handles the heavy lifting of deep site analysis. It lets your OpenAI agent ingest whole knowledge bases without hitting memory limits or timing out during long HTTP requests.

Setup guide

Set up Firecrawl 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 Firecrawl tools at runtime.
3

Create your Agent

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

Run the agent

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

The Firecrawl MCP Server handles backoff internally when scraping large sites. Your OpenAI agent receives clean data without needing custom retry logic in your Python code.

Yes, you can filter the tool list during initialization. This prevents your OpenAI agent from executing deep crawls when it only needs simple single-page scraping.

You set the API key in your server environment variables on Vinkius. The MCP Server connects to the single secure endpoint, meaning your client code never exposes raw credentials.

The `crawl_site` tool returns an async job ID immediately. Your agent can poll the status or execute other tasks instead of hanging the connection.

Your scraped Markdown and URLs pass through a secure V8 sandbox on Vinkius before reaching your OpenAI client. No scraped web content is stored permanently on our servers, ensuring your data pipeline remains ephemeral 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