How to Use the Firecrawl MCP in OpenAI Agents SDK

Q: How do I monitor Firecrawl usage within OpenAI Agents SDK?

Use the getapiusage tool. It returns your current credit count, so you can programmatically block or throttle your agent if you approach your monthly limit.

Q: Can I stop a stuck Firecrawl job in OpenAI Agents SDK?

Absolutely. You trigger cancelactivecrawl with your job ID. It kills the process on the server side to save your credits.

Convert messy web content into clean markdown for your OpenAI Agents SDK production pipelines.

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

Scrape content for OpenAI Agents SDK

Use `scrape_url` to pull clean markdown directly into your agent's context window. It handles complex JavaScript rendering so your agent works with the actual page content, not just the raw HTML source. This keeps your agent's reasoning focused on relevant text. You spend less time debugging parsing errors and more time building your application's core logic.

Manage large crawls in OpenAI Agents SDK

Trigger `start_crawl` to index entire domains asynchronously. Your agent receives a job ID, allowing it to move on to other tasks while the server processes the requested site structure. Monitor your progress using `get_crawl_status` within your event loop. If a crawl runs too long or hits a rate limit, call `cancel_active_crawl` to clean up resources immediately.

Track costs in OpenAI Agents SDK

Call `get_api_usage` to verify your remaining credits before initiating large scraping jobs. Keeping these metrics visible ensures your production agent system stays within budget. `map_website_structure` helps you audit a site's depth before committing to a full scrape. This prevents accidental consumption of your entire API quota on massive, irrelevant subdirectories.

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

Use the `get_api_usage` tool. It returns your current credit count, so you can programmatically block or throttle your agent if you approach your monthly limit.

Yes. Firecrawl renders JavaScript before it returns the markdown. Your agent sees the final state of the page, which is critical for modern web apps.

Absolutely. You trigger `cancel_active_crawl` with your job ID. It kills the process on the server side to save your credits.

Your data is ephemeral. Vinkius manages the connection, and the server only processes the URLs you explicitly pass to the tools.

It gives you a map of the site. You avoid scraping dead ends and ensure your agent only ingests the high-value pages you actually need.

Use it with your favorite AI tools

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