Can my AI remotely trigger a payment on one of my physical Bold terminals?

Yes! Use the `initiate_terminal_payment` tool with the terminal serial number and amount in COP. The datáfono will immediately display the checkout screen for the customer to tap or insert their card.

How do I generate a payment link that I can share with my customers via WhatsApp or email?

Simply ask the agent to run `create_payment_link` with the amount in COP and a description. You'll receive a unique URL that your customers can open to complete the payment securely through Bold's hosted checkout.

Can I check my settlement balance and pending disbursements through my AI agent?

Absolutely. The `get_account_balance` tool returns your real-time available balance and pending settlement amounts in COP, giving you instant financial visibility without logging into the Bold dashboard.

Bold MCP Server for CrewAI 14 tools — connect in under 2 minutes

Name: Bold
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 14 Tools Framework

Connect your CrewAI agents to Bold through Vinkius, pass the Edge URL in the `mcps` parameter and every Bold 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="Bold Specialist",
    goal="Help users interact with Bold effectively",
    backstory=(
        "You are an expert at leveraging Bold 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 Bold "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 14 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 Bold MCP Server

Connect your Bold merchant account to any AI agent and gain full control of your Colombian payment infrastructure through natural conversation.

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

What you can do

Terminal Management — List all bound datáfono devices (Smart Pro, Smart Mini) and trigger in-store payment flows remotely
Online Payments — Process card-not-present payments, create shareable payment links, and manage the full transaction lifecycle
Transaction Intelligence — Query historical transactions by date range, inspect individual payment details including card brand and settlement data
Refund Operations — Issue full reversals on approved online payments back to the original payment method
Webhook Configuration — Register and manage real-time HTTPS endpoints for transaction event notifications
Balance Monitoring — Check your merchant account balance including available funds and pending disbursements

The Bold MCP Server exposes 14 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 Bold to CrewAI via MCP

Follow these steps to integrate the Bold 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 14 tools from Bold

Why Use CrewAI with the Bold MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Bold 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 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

Bold + CrewAI Use Cases

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

Automated multi-step research: a reconnaissance agent queries Bold 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 Bold, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Bold 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 Bold against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Bold MCP Tools for CrewAI (14)

These 14 tools become available when you connect Bold to CrewAI via MCP:

create_online_payment

Requires card tokenization details, the amount in COP, and payer information for Colombian anti-fraud compliance. Process an online card payment

create_payment_link

The link includes the specified amount in Colombian Pesos (COP) and a reference description. Generate a shareable payment link

create_webhook

) in your Bold merchant account. Register a new webhook endpoint

delete_webhook

Remove a webhook endpoint

get_account_balance

Get current merchant account balance

get_online_payment

Get details of an online payment

get_payment_link

Get details of a specific payment link

get_transaction

Get details of a specific transaction

initiate_terminal_payment

This requires the terminal serial number and the payment amount in COP. Trigger a payment on a physical terminal

list_payment_methods

List accepted payment methods

list_terminals

) currently linked to your Bold merchant account, including their serial numbers and connectivity status. List all bound payment terminals

list_transactions

List recent payment transactions

list_webhooks

List configured webhooks

refund_payment

The refund is processed back to the original payment method and may take 5-10 business days to reflect on the cardholder's statement. Issue a refund for a processed payment

Example Prompts for Bold in CrewAI

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

"Show me all the datáfono terminals connected to my Bold account."

"Create a payment link for 150,000 COP for the invoice #INV-2024-089."

"List all transactions from the last 7 days and show me the total processed."

Troubleshooting Bold MCP Server with CrewAI

Common issues when connecting Bold 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

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

Bold + CrewAI FAQ

Common questions about integrating Bold 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.