How to Use the Firecrawl MCP in CrewAI

Q: How do I connect Firecrawl to my CrewAI agents?

Pass the Vinkius URL into the mcps parameter of your Agent definition. Your agents will automatically detect and list the available tools.

Q: How does Firecrawl handle site-wide search in CrewAI?

The searchweb tool is designed for this. You provide the search query, and the tool returns structured Markdown that your agents can parse instantly.

Q: Can I limit which Firecrawl tools my agents use?

Use the toolfilter in your CrewAI MCP configuration. You can restrict agents to only use specific tools like scrapepage if that is all they need.

Deploy a specialized research crew with the Firecrawl MCP Server for autonomous operations.

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 CrewAI

Create your Vinkius account to connect Firecrawl to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous research with CrewAI

Let your research agent use `search_web` to find information and `scrape_page` to pull the text. It functions exactly like a browser-enabled assistant. Your agents collaborate to parse the results. One agent finds the links, another scrapes the data, and the final agent summarizes it for you.

Deep site context for your crew

Use `crawl_site` to feed large amounts of documentation into your crew's shared memory. Your agents can then answer questions based on the entire site context. This is ideal for monitoring changes on target pages. Set your crew to run on a schedule, and they will keep your data up to date without manual input.

Efficient site navigation

Call `map_site` to have an agent identify the relevant pages before starting a deep extraction. This prevents your crew from wasting resources on irrelevant pages. It keeps your agentic operations efficient and focused. You only extract the content that directly contributes to your crew's final goal.

Setup guide

Set up Firecrawl MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Firecrawl tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Firecrawl Analyst",
    goal="Access and analyze Firecrawl data via MCP.",
    backstory="Expert analyst with direct Firecrawl access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Firecrawl transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Firecrawl Analyst",
        goal="Access and analyze Firecrawl data via MCP.",
        backstory="Expert analyst with direct Firecrawl access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Firecrawl transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the Vinkius URL into the `mcps` parameter of your Agent definition. Your agents will automatically detect and list the available tools.

Yes. CrewAI supports shared memory. Once one agent scrapes a page, the result is available to the rest of the crew for analysis.

The `search_web` tool is designed for this. You provide the search query, and the tool returns structured Markdown that your agents can parse instantly.

Use the `tool_filter` in your CrewAI MCP configuration. You can restrict agents to only use specific tools like `scrape_page` if that is all they need.

Security is absolute. We do not store your extracted text or site structure. Each request is isolated in our V8 sandbox, ensuring your research remains 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