How to Use the Nimbleway MCP in CrewAI

Q: How do I set up Nimbleway with a CrewAI agent?

Pass the server URL to your agent's mcps parameter. Once connected, your agents can call tools like searchweb as if they were local functions.

Q: What happens if a scraping job takes too long in CrewAI?

You can configure your agents to poll getjob until completion. If it exceeds your time limit, the agent can escalate the issue to a supervisor for a decision.

Deploy a specialized crew of agents to crawl the web. Use CrewAI for autonomous operations and complex data research.

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 CrewAI

Create your Vinkius account to connect Nimbleway 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 Nimbleway with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent research crews

Assign research tasks to specific agents while keeping your logic organized. Use `search_web` to gather intelligence and `extract_markdown` to feed that data to your analysis agents. Your crew collaborates by sharing the results from these tools. One agent finds the links, another cleans the content, and the final agent writes the report.

Headless scraping operations

Run your data collection in the background without human intervention. The MCP Server acts as the interface for your agents to interact with live websites. Coordinate sequential or hierarchical tasks to ensure your crew finishes the job. It works perfectly for long-running monitoring or competitive intelligence reports.

Pipeline and job management

Monitor the health of your scraping operations using `list_jobs` and `get_pipeline`. Your agents can check these to see if they need to adjust their strategy. Keep your operations efficient by checking account metrics. If a job stalls, the agent identifies the issue and reports it back to the moderator.

Setup guide

Set up Nimbleway 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 Nimbleway tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Nimbleway 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 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 CrewAI

Pass the server URL to your agent's `mcps` parameter. Once connected, your agents can call tools like `search_web` as if they were local functions.

Yes. Use a tool filter in your MCP configuration to give the researcher agent access to `search_web` while limiting the analyst agent to `extract_markdown`.

CrewAI agents use shared memory to track the progress of their scraping tasks. This helps the crew avoid duplicate work and stay focused on the objective.

You can configure your agents to poll `get_job` until completion. If it exceeds your time limit, the agent can escalate the issue to a supervisor for a decision.

The server only processes public web data. It does not access your internal files or private accounts, ensuring your agent operations remain isolated and secure.

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