How to Use the Dubsado MCP in CrewAI

Q: How do CrewAI agents collaborate on a Dubsado project?

Your intake agent uses createproject to initialize the record, then shares the project ID via CrewAI's shared memory over the MCP connection. A second onboarding agent picks up the ID to execute applyworkflow and set up the task list.

Q: Can a CrewAI agent draft a new Dubsado invoice autonomously?

Yes, your billing agent can trigger createinvoice using parameters parsed from your project files. The agent calculates the totals, writes the invoice, and passes the details to a delivery agent.

Q: How do I restrict which Dubsado tools my CrewAI agents can access?

Use the MCPServerHTTP class with a toolfilter to only expose specific tools like listprojects to your agents. This prevents research agents from accidentally triggering write actions like updateproject.

Q: What is the benefit of using this MCP Server for client onboarding?

This server allows your agents to directly query listworkflowtemplates and apply them instantly. It removes the need to write custom API integrations, letting you connect your workspace to your agent team in minutes.

Q: Is my Dubsado contact data safe from being trained on by CrewAI?

Yes, contact records retrieved via listcontacts are passed directly to your local or private agent execution context. This MCP Server does not store, cache, or share client names, emails, or phone numbers with any external LLM providers.

Deploy a crew of specialized CrewAI agents to manage your Dubsado projects, contracts, and invoices autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dubsado MCP to CrewAI

Create your Vinkius account to connect Dubsado 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 Dubsado with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate project setups using CrewAI

`create_project` runs when your intake agent identifies a qualified lead in your inbox. The agent passes the new project ID to the coordinator agent, who handles the next setup phases. From there, `update_project` updates timelines and deliverables based on the client's initial brief. This multi-agent handoff ensures your workspace is fully prepared before a human account manager ever logs in.

Audit agreements with this MCP Server

`list_contracts` allows your legal audit agent to gather all pending agreements across active folders. The agent cross-references these files to spot unsigned documents. Once identified, `get_contract` retrieves the specific terms and signature status for the bottlenecked file. Your follow-up agent then drafts a targeted reminder based on the exact missing signatures.

Manage billing cycles autonomously

`list_invoices` gives your finance crew a complete view of outstanding balances for the month. The billing agent categorizes these invoices by due date to prioritize follow-ups. For overdue accounts, `create_invoice` can generate late-fee adjustments or follow-up payment links. The crew executes these steps sequentially, updating your ledger without manual intervention.

Setup guide

Set up Dubsado 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 Dubsado tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Your intake agent uses `create_project` to initialize the record, then shares the project ID via CrewAI's shared memory over the MCP connection. A second onboarding agent picks up the ID to execute `apply_workflow` and set up the task list.

Yes, your billing agent can trigger `create_invoice` using parameters parsed from your project files. The agent calculates the totals, writes the invoice, and passes the details to a delivery agent.

Use the `MCPServerHTTP` class with a `tool_filter` to only expose specific tools like `list_projects` to your agents. This prevents research agents from accidentally triggering write actions like `update_project`.

This server allows your agents to directly query `list_workflow_templates` and apply them instantly. It removes the need to write custom API integrations, letting you connect your workspace to your agent team in minutes.

Yes, contact records retrieved via `list_contacts` are passed directly to your local or private agent execution context. This MCP Server does not store, cache, or share client names, emails, or phone numbers with any external LLM providers.

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