How to Use the Diese MCP in CrewAI

Q: Does my CrewAI setup support selective tool access for Diese?

You control what your agents see. Use the toolfilter parameter to limit access to specific functions like project lists or invoice lookups. This keeps your agent operations focused.

Get your CrewAI agents to manage ERP projects and invoices directly through this Diese 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 Diese MCP to CrewAI

Create your Vinkius account to connect Diese 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 Diese with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate project tracking with Diese MCP Server

Your CrewAI agents can now pull live project data without manual exports. Use `list_erp_projects` to keep your multi-agent team updated on active work or `get_project_details` to feed specific specs to your research agents. Stop guessing project status. When you trigger `search_projects_by_name`, the agent finds the exact folder you need. It turns raw ERP data into actionable intelligence for your entire crew.

Monitor financial health using Diese in CrewAI

Your finance agent can track payment cycles by calling `list_sales_invoices` in real-time. It checks status updates and flags discrepancies before they become bottlenecks. Keep tabs on costs with `list_business_expenses`. Your agents can reconcile these records against project budgets during their analysis phase, ensuring no line item slips through the cracks.

Coordinate resource planning in CrewAI

Resource allocation becomes a background task for your agents. By querying `list_resource_planning` and `list_project_tasks`, the crew knows exactly who is working on what without human pestering. Catch delays early with `list_overdue_erp_tasks`. Your moderator agent can escalate these items to the right manager immediately, keeping your operations moving on schedule.

Setup guide

Set up Diese 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 Diese tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You install the server and point your agents to the endpoint. Simply include the server URL in your agent definition's mcps list. It connects the API to your crew's shared memory.

Yes, your agents call the tool directly. It scans your ERP data for missed deadlines. Your crew can then prioritize these items in their next sprint.

You control what your agents see. Use the tool_filter parameter to limit access to specific functions like project lists or invoice lookups. This keeps your agent operations focused.

You provide one endpoint token during setup. The server manages the session handshake for you. Your agents just execute the tools.

Your data remains in your environment. The server acts as a bridge, only passing the specific invoice records requested by your agents. No data is stored in the transport layer.

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