How to Use the Daftra MCP in CrewAI

Q: How do I assign different Daftra tools to specialized agents in CrewAI?

When you define an Agent in CrewAI, you can use the toolfilter argument on the MCP Server configuration. This lets you expose only specific tools, like listinvoices, to that one agent, enforcing role specialization.

Deploy autonomous agent crews to run your Daftra ERP. Set up a team to monitor finances, manage clients, and act on its findings without you.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daftra MCP to CrewAI

Create your Vinkius account to connect Daftra 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 Daftra with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an Autonomous Accounts Receivable Crew

Build an autonomous crew to chase down late payments. One agent, the 'Auditor,' can run `list_invoices` on a schedule to find overdue accounts. It passes the list to a second agent, the 'Investigator,' which uses `get_client_details` to check each client's payment history and status. This is how you automate an entire department's function. The crew works together, sharing information through their shared memory to complete a complex task that a single agent couldn't handle alone.

Deploy an Inventory and Sales Analysis Team

Put a crew in charge of your inventory and sales analysis. An 'Inventory Clerk' agent can use `list_inventory_products` to monitor your catalog. A 'Sales Analyst' agent can then take that product list and use `list_invoices` to find sales trends for specific items. Because CrewAI agents can operate sequentially, the Analyst can wait for the Clerk to finish its work before starting its own. This creates a powerful, automated reporting pipeline for your Daftra data.

Reconcile Data with a CrewAI MCP Server

Use a dedicated CrewAI team with this MCP Server to keep your client data in sync across different systems. For example, a 'Finder' agent can use `search_clients_by_name` in Daftra while another agent checks a separate database. A 'Validator' agent then compares the two records. Based on its findings, it can delegate the task of adding a missing record to an 'Onboarder' agent, which has access to the `create_client` tool. It's a fully autonomous data-hygiene crew.

Setup guide

Set up Daftra 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 Daftra tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

When you define an Agent in CrewAI, you can use the `tool_filter` argument on the MCP Server configuration. This lets you expose only specific tools, like `list_invoices`, to that one agent, enforcing role specialization.

Absolutely. You can create one agent that's an expert in invoices using `list_invoices` and `get_invoice_details`, and another that's an expert in clients using `list_clients` and `create_client`. They can then collaborate on tasks, passing client IDs and invoice numbers between them.

The easiest way is to pass the Vinkius URL directly into the `mcps` list when you define your Agent. CrewAI will automatically fetch the tools and make them available.

Yes, that's a perfect use case for CrewAI's hierarchical process. You can have a manager agent that tasks a 'Monitor' agent to periodically run `list_expenses`, and if a certain condition is met, it tasks an 'Action' agent to perform a follow-up operation.

Your Daftra client names, contact details, and product pricing are processed in memory only. Each request runs in a fresh V8 Isolate sandbox, completely cut off from everything else. The token your agent uses is scoped only to that single operation, then it's gone.

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