How to Use the Dext MCP in CrewAI

Q: How does my crew get a list of all our clients from Dext?

Assign an agent the listaccountingclients tool. When its task runs, it can execute that tool to get a complete list of clients associated with your partner account and share that information with the rest of the crew.

Deploy a crew of autonomous agents with CrewAI to manage your entire Dext accounting process.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dext MCP to CrewAI

Create your Vinkius account to connect Dext 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 Dext with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an AP Agent Crew

Don't build one bot, build a team. With CrewAI, you can assign one agent the 'Auditor' role, constantly monitoring `list_items_pending_review`. When it finds an item, it passes it to the 'Bookkeeper' agent. The 'Bookkeeper' agent then uses `get_item_details` and `list_accounting_categories` to classify the transaction. If it's a new supplier not found in `list_extracted_suppliers`, it delegates the task to another agent for human review. That’s a real autonomous workflow.

Autonomous Client Monitoring

Set up a 'Client Manager' agent whose only job is to run `list_accounting_clients` and loop through each one. For each client, it can delegate a check to a 'Health Check' agent. The 'Health Check' agent verifies account status using `get_account_metadata` and confirms `list_connected_bank_accounts` are active. If it finds an issue, it can log a ticket or escalate, all without you lifting a finger. This is what the Dext MCP Server enables.

Specialized Roles for CrewAI Agents

CrewAI lets you get specific. Create a 'Researcher' agent that only has access to search tools like `search_inbox_by_keyword`. Its job is to find historical data on a supplier and pass a summary to the team. Meanwhile, an 'Admin' agent can manage the team roster by checking `list_account_users`, ensuring the right people are notified. By giving each agent a limited toolset from this MCP, you build a more robust and secure system.

Setup guide

Set up Dext 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 Dext tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

When you define your agent in CrewAI, you can provide a filtered list of tools. This allows you to create specialized agents, like an 'Auditor' that can only use `list_items_pending_review` and a 'Clerk' that can use `get_item_details`.

Yes, that's a perfect use case. Define an agent with a recurring task and give it access only to the `list_inbox_items` tool. Its entire job will be to watch the inbox and delegate any findings to other agents.

Definitely. You can set up a sequential process where one agent fetches an invoice from Dext, a second agent analyzes it, and a third agent presents it for human approval if it meets certain criteria. CrewAI is built for these kinds of multi-agent workflows.

Assign an agent the `list_accounting_clients` tool. When its task runs, it can execute that tool to get a complete list of clients associated with your partner account and share that information with the rest of the crew.

Each agent's tool use is executed in a Vinkius V8 Isolate Sandbox, which is destroyed after the call. The Dext MCP server is stateless and doesn't persist any of the accounting data—like supplier lists or item details—it touches. Your CrewAI agents interact with the tools through a secure endpoint, and the data exists only in memory, during the task.

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