How to Use the Holded MCP in CrewAI

Q: How do I give my CrewAI agents access to the Holded MCP server?

It's straightforward. After pip install crewaitools, you pass the server URL directly into your Agent definition using the mcps parameter, like this: mcps='https://...'. CrewAI handles the connection automatically.

Q: Can I make a CrewAI agent that only manages Holded inventory?

Yes. Instead of the simple setup, use the MCPServerHTTP class from crewai.mcp. It has a toolfilter argument that lets you expose only specific tools, like listproducts and updateproductstock, to a specialist agent.

Assemble an autonomous crew of AI agents to run your Holded operations. CrewAI makes them work together.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Holded MCP to CrewAI

Create your Vinkius account to connect Holded 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 Holded with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy an Autonomous Accounting Crew

Don't just run one agent, run a team. Assign a 'Clerk' agent to use `list_invoices` to find new entries. An 'Auditor' agent can then take those invoices, use `get_invoice_details`, and cross-reference them with project data from `get_project_details` to ensure accuracy. This is possible because the MCP server exposes the right tools for each agent's job. The crew shares context and passes tasks between members, creating a system that can manage your Holded finances autonomously.

Run Inventory with a CrewAI Team

Build a specialized crew for supply chain management. A 'Scout' agent can monitor incoming sales data from other systems. It then tasks the 'Quartermaster' agent to use the `update_product_stock` tool in Holded to keep inventory levels accurate. Meanwhile, a 'Planner' agent can run `list_products` on a schedule, analyze sales velocity, and flag items that need to be reordered. Each agent has a specific role, and they collaborate to keep your inventory in check without any manual work.

Automate Project Oversight with CrewAI

Set up a 'Supervisor' agent to watch over your business. It can periodically run `list_projects` to get a high-level status of all ongoing work. Based on the data, it can identify projects that are falling behind schedule. When it spots a problem, it delegates to an 'Investigator' agent. This second agent uses `get_project_details` and `list_all_tasks` to find the specific bottleneck and can then alert a human manager with a concise summary. This MCP server is the crew's direct line into your Holded data.

Setup guide

Set up Holded 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 Holded tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

It's straightforward. After `pip install crewai[tools]`, you pass the server URL directly into your Agent definition using the `mcps` parameter, like this: `mcps=['https://...']`. CrewAI handles the connection automatically.

Yes. Instead of the simple setup, use the `MCPServerHTTP` class from `crewai.mcp`. It has a `tool_filter` argument that lets you expose only specific tools, like `list_products` and `update_product_stock`, to a specialist agent.

You'd create separate agents with distinct roles. For example, one agent's job is to use `list_invoices` to find overdue payments. It then passes the invoice ID to a second agent, whose job is to use `get_contact_details` and send a notification.

Absolutely. You can create a dedicated 'Monitor' agent with a recurring task to run `list_projects`. You can define its goal to analyze the output and identify projects with upcoming deadlines or those that haven't shown recent activity.

Yes. Data like product details and stock levels are handled securely. The connection from your CrewAI environment to Holded is a direct, encrypted tunnel that passes through an isolated Vinkius sandbox. The server is stateless, meaning it doesn't store or log any of your business data.

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