How to Use the Bleez MCP in CrewAI

Q: How do agents handle errors when a customer lookup fails?

If listcustomers returns an empty result, your agent can use its internal reasoning to decide whether to create a new profile or escalate the issue to a human manager.

Deploy specialized agent teams to run your Brazilian e-commerce operations autonomously using CrewAI and this 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 Bleez MCP to CrewAI

Create your Vinkius account to connect Bleez 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 Bleez with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent bookkeeping and ledger validation

The `create_accounting_entry` tool allows your digital books to stay updated through the MCP Server without human intervention. Inside CrewAI, you can assign a Bookkeeper Agent to draft the entry, while an Auditor Agent uses `list_accounting_entries` to verify the accuracy against your records. This division of labor prevents errors in your Brazilian tax filings. The agents collaborate in real-time, passing context back and forth until the numbers match perfectly.

Autonomous billing with CrewAI agent teams

The `list_customers` tool lets your agent team analyze buyer behavior and payment history. A Billing Agent can query this list, identify accounts with outstanding balances, and use `create_invoice` to issue new payment requests automatically. This keeps your cash flow steady without requiring your staff to manually audit accounts. The entire process runs in the background based on your crew's schedule.

Automated document ingestion and routing

The `upload_document` tool processes incoming physical or digital receipts into your document-management system. A Clerk Agent can monitor an inbox, upload the documents, and hand off the resulting metadata to a Manager Agent. The Manager Agent then runs `get_account_info` to ensure the correct tax settings are applied. This turns a tedious paper trail into a structured, searchable database.

Setup guide

Set up Bleez 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 Bleez tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Bleez 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 Bleez. 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 Bleez 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 Bleez MCP in CrewAI

Pass your Vinkius HTTP URL directly into the agent's mcps parameter. The framework automatically discovers tools like list_invoices and makes them available to your agents.

Yes, CrewAI allows you to restrict tool access. You can give your Billing Agent access to create_invoice, while your Auditor Agent only gets list_invoices to check the results.

Yes, you can chain tasks together using the MCP Server. For example, Task 1 can upload a file using upload_document, and Task 2 can immediately run create_accounting_entry using the output from the first step.

If list_customers returns an empty result, your agent can use its internal reasoning to decide whether to create a new profile or escalate the issue to a human manager.

All interactions with your ledger, customer lists, and supplier profiles are secured via TLS and processed in zero-trust sandboxes. Vinkius manages the authentication tokens centrally, so your agents never have direct access to raw database credentials.

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