How do I get a Cradl AI API Key?

Log in to your Cradl AI dashboard and navigate to the API section to generate a new key. Ensure you keep this key secure.

Which document formats are supported?

Cradl AI supports major formats including PDF, JPEG, PNG, and TIFF for data extraction.

Can I train custom models via chat?

This integration currently focuses on executing extractions and monitoring tasks. Model training should be performed through the Cradl AI dashboard.

Cradl AI MCP Server for CrewAI 10 tools — connect in under 2 minutes

Name: Cradl AI
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 10 Tools Framework

Connect your CrewAI agents to Cradl AI through the Vinkius — pass the Edge URL in the `mcps` parameter and every Cradl AI tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Cradl AI Specialist",
    goal="Help users interact with Cradl AI effectively",
    backstory=(
        "You are an expert at leveraging Cradl AI tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token — get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Cradl AI "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 10 available tools "
        "and what they can do."
    ),
)

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

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Cradl AI MCP Server

Integrate Cradl AI, the advanced document data extraction platform, directly into your AI workflow. Automate the processing of invoices, receipts, IDs, and custom forms using powerful deep learning models and natural language.

When paired with CrewAI, Cradl AI becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Cradl AI tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.

What you can do

Data Extraction — Trigger real-time data extraction from document URLs with high precision.
Model Management — List and explore your custom-trained extraction models.
Workflow Monitoring — Track the status of document processing flows and individual tasks.
Batch Processing — Audit and retrieve details for entire batches of processed documents.

The Cradl AI MCP Server exposes 10 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Cradl AI to CrewAI via MCP

Follow these steps to integrate the Cradl AI MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py — CrewAI auto-discovers 10 tools from Cradl AI

Why Use CrewAI with the Cradl AI MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Cradl AI through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles — one agent researches, another analyzes, a third generates reports — each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass the Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Cradl AI + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Cradl AI MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Cradl AI for raw data, then a second analyst agent cross-references findings and flags anomalies — all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Cradl AI, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Cradl AI tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Cradl AI against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Cradl AI MCP Tools for CrewAI (10)

These 10 tools become available when you connect Cradl AI to CrewAI via MCP:

extract_data_from_url

Touches OCR engine, model prediction, and data normalization boundary. Trigger a new data extraction prediction from a file URL

get_batch_details

Touches individual file statuses and batch-level processing summary boundaries. Get details for a specific batch of documents

get_flow_details

Touches integration points and document routing rules boundaries. Get structure and settings for a specific flow

get_model_details

Touches schema definitions, extraction accuracy metrics, and model metadata boundaries. Get details for a specific extraction model

get_task_status

Resolves confidence scores and extracted key-value pairs from the document. Check the status and results of a document task

list_batches

Resolves batch identifiers, creation dates, and total document counts within each batch. List all document batches

list_extraction_models

Resolves model names, versions, and training statuses for document analysis. List all data extraction models in Cradl AI

list_processing_tasks

Resolves task IDs, statuses (PENDING, COMPLETED, FAILED), and processing timestamps. List recent document processing tasks

list_workflows

Resolves flow IDs, triggers, and configured processing steps. List all document processing flows

search_models_by_name

Resolves model metadata based on a name keyword search. Search for extraction models by name

Example Prompts for Cradl AI in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Cradl AI immediately.

"Extract data from this invoice: https://example.com/inv123.pdf using my 'Invoice Parser' model."

"Check the status of document processing task 't8s9df7'."

"List all extraction models available in my account."

Troubleshooting Cradl AI MCP Server with CrewAI

Common issues when connecting Cradl AI to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts — check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

The Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Cradl AI + CrewAI FAQ

Common questions about integrating Cradl AI MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily — when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.