How to Use the Cradl AI MCP in CrewAI

Q: How do I pass Cradl AI tools to a CrewAI agent?

You can pass the Vinkius MCP Server URL directly into the mcps array when defining your CrewAI agent. This gives that specific agent access to tools like extractdatafromurl without affecting other agents in the crew.

Q: How do CrewAI agents handle document extraction errors from Cradl AI?

If extractdatafromurl fails, the active agent can log the error to the crew's shared memory. A supervisor agent can then intervene, switching models or routing the task to a different worker.

Deploy specialized teams of agents to process, audit, and route documents using CrewAI and the Cradl AI MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cradl AI MCP to CrewAI

Create your Vinkius account to connect Cradl 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 Cradl AI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent document auditing crews

CrewAI shines when agents collaborate. You can assign one agent to trigger `extract_data_from_url` while a separate auditor agent uses `get_task_status` to verify the confidence scores of the extracted fields. This division of labor stops bad data from slipping into your database. The auditor agent can flag low-confidence extractions and hand them off to a manager agent for manual review.

Automated batch management via CrewAI

Managing massive queues of documents requires coordination. Set up a manager agent to monitor your pipeline using `list_batches` and assign specific batches to worker agents. The worker agents then drill down into `get_batch_details` to process files in parallel. This sequential execution keeps your document queue moving without overloading your API limits.

Dynamic workflow adaptation

Let your crew figure out how to process new document types. An agent can call `list_workflows` to see active business rules and decide where to route a freshly parsed PDF. If the current rules don't cover the document, the agent uses `list_processing_tasks` to find similar historically successful tasks and replicate their processing steps autonomously.

Setup guide

Set up Cradl 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 Cradl AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can pass the Vinkius MCP Server URL directly into the `mcps` array when defining your CrewAI agent. This gives that specific agent access to tools like `extract_data_from_url` without affecting other agents in the crew.

Yes, CrewAI supports hierarchical and sequential execution where different agents can call `get_task_status` and `list_batches` in parallel, sharing the results through their common memory.

If `extract_data_from_url` fails, the active agent can log the error to the crew's shared memory. A supervisor agent can then intervene, switching models or routing the task to a different worker.

No. CrewAI's integration handles the underlying MCP Server transport automatically, meaning your agents can focus entirely on calling `list_workflows` and processing documents.

Yes. All data processed through this MCP Server is protected by Vinkius's V8 Isolate Sandbox. Your scanned receipts and tax forms are processed in memory and destroyed immediately after the tools finish 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