How to Use the Browse AI MCP in CrewAI

Q: How do CrewAI agents coordinate to run a Browse AI scraper?

You assign one agent to select the robot using listrobots through this MCP Server and another to execute it via triggerrobotrun. They share memory to pass the robot ID and parameters between tasks.

Q: Can my CrewAI agents check my remaining Browse AI scraping credits?

Yes, your analyst agent can call getusagequotas to monitor your Browse AI credit balance. This allows the crew to pause scraping operations if you are running low on credits.

Q: How do CrewAI agents handle webhooks for completed Browse AI scrapes?

An agent can call listrobotwebhooks to inspect current configurations. If a webhook needs to be replaced, the agent can clean it up using removewebhook automatically.

Deploy a crew of specialized CrewAI agents to scrape, monitor, and analyze web data autonomously with Browse AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browse AI MCP to CrewAI

Create your Vinkius account to connect Browse AI 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 Browse AI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Scraping Pipelines in CrewAI

Assign one agent to find the right scraper while another executes it using this MCP Server. Your researcher agent calls `list_robots` to find the correct tool, then passes the ID to your execution agent. The execution agent starts the extraction by calling `trigger_robot_run`. This division of labor keeps your autonomous operations organized and prevents single-agent bottlenecks.

Autonomous Scraper Performance Auditing

Let a manager agent oversee your scraping history. The auditor agent calls `list_robot_history` to pull past execution logs and identify patterns in failed runs. If a specific scraper keeps failing, the agent checks `get_robot_details` to see if the target website changed its layout. This lets your crew flag broken scrapers before they disrupt your business.

Self-Managing Scraping Schedules via MCP Server

Your crew can scale your monitoring operations up or down based on data needs. An operations agent checks active schedules using `list_active_monitors` to see what is currently running. If a tracking task is no longer needed, the agent removes the schedule. If a new competitor site needs tracking, it calls `create_monitor` to start tracking it automatically.

Setup guide

Set up Browse AI 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 Browse AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Browse AI 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="Browse AI Analyst",
        goal="Access and analyze Browse AI data via MCP.",
        backstory="Expert analyst with direct Browse AI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Browse AI 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 Browse AI. 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 Browse AI 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 Browse AI MCP in CrewAI

You assign one agent to select the robot using `list_robots` through this MCP Server and another to execute it via `trigger_robot_run`. They share memory to pass the robot ID and parameters between tasks.

Yes, your analyst agent can call `get_usage_quotas` to monitor your Browse AI credit balance. This allows the crew to pause scraping operations if you are running low on credits.

An agent can call `list_robot_webhooks` to inspect current configurations. If a webhook needs to be replaced, the agent can clean it up using `remove_webhook` automatically.

Yes, you can use CrewAI's tool filtering to expose only specific capabilities like `get_run_status` to your monitoring agents while keeping admin tools restricted.

Yes, it is. Vinkius secures your Browse AI credentials and extracted data tables using end-to-end encryption. The server runs in a stateless, ephemeral sandbox that destroys all session data immediately after the agent finishes its execution.

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