How do I securely obtain my Conekta Private API Key?

Log in to your Conekta dashboard as an administrator. In the left sidebar, click on 'Developers' (Desarrolladores), then navigate to 'API Keys' (Llaves API). Locate the 'Private Key' (Llave Privada) section—you may need to enter your password to reveal it. Copy this key and paste it into the secure input field below to connect the agent.

Can the AI agent create new charges or issue refunds directly?

No. This integration operates strictly in read-only mode to guarantee financial security. The conversational agent can query and extract data regarding transactions, customers, and overall payments, but it cannot authorize new charges or initiate refunds, protecting your account from unintended financial actions.

What kind of data can I ask the agent to retrieve from Conekta?

You can ask the agent to check the exact status of a specific payment ID, verify whether a charge was approved or declined, list recent successful orders, or summarize the daily transaction volume and associated processing fees.

Conekta MCP Server for CrewAI 8 tools — connect in under 2 minutes

Name: Conekta
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 8 Tools Framework

Connect your CrewAI agents to Conekta through Vinkius, pass the Edge URL in the `mcps` parameter and every Conekta 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="Conekta Specialist",
    goal="Help users interact with Conekta effectively",
    backstory=(
        "You are an expert at leveraging Conekta 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 Conekta "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 8 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 Conekta MCP Server

Integrate your AI assistant with Conekta, the leading online payment gateway in Mexico and Latin America. By providing seamless connectivity to your Conekta account, your conversational agent can instantly analyze transaction data, verify specific charges, and keep track of your core e-commerce metrics directly through natural language requests.

When paired with CrewAI, Conekta becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Conekta 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

Transaction Lookups — Instantly query the status of specific payments by providing a transaction ID or customer email.
Sales Analysis — Ask for summaries of recent successful transactions, refunds, or chargebacks to keep track of store performance.
Customer Management — Retrieve and review customer profiles and their associated payment history to provide faster support.

The Conekta MCP Server exposes 8 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 Conekta to CrewAI via MCP

Follow these steps to integrate the Conekta 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 8 tools from Conekta

Why Use CrewAI with the Conekta MCP Server

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

Conekta + CrewAI Use Cases

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

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

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

Conekta MCP Tools for CrewAI (8)

These 8 tools become available when you connect Conekta to CrewAI via MCP:

create_order

Requires customer name, email, phone, and at least one line item with name, unit_price (in cents), and quantity. Currency defaults to MXN. Create a new order in Conekta

get_customer

Returns contact info, payment sources, and order history. Retrieve detailed information about a specific customer

get_order

Returns charges, line items, customer info, and payment status. Retrieve detailed information about a specific order

list_customers

Retrieve a list of customer records from Conekta

list_events

Useful for debugging integrations. Retrieve a list of API events (webhook history)

list_orders

Use payment_status filter to narrow results. Supports limit for pagination. Retrieve a paginated list of orders from Conekta

list_subscription_plans

Retrieve a list of subscription plans in Conekta

search_customer_by_email

Returns matching customer profiles. Find a Conekta customer by their email address

Example Prompts for Conekta in CrewAI

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

"Check if the Conekta payment with ID 'ord_2nx...4kx' was successfully processed or declined."

"Summarize today's approved transactions and total revenue in MXN."

"List the last 5 chargebacks or disputed claims in our account."

Troubleshooting Conekta MCP Server with CrewAI

Common issues when connecting Conekta 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.

Conekta + CrewAI FAQ

Common questions about integrating Conekta 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.