How to Use the Moxie MCP in CrewAI

Deploy autonomous agent crews to run your agency. With CrewAI and Moxie, you can automate project management, finance, and client operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moxie MCP to CrewAI

Create your Vinkius account to connect Moxie 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 Moxie with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy an Autonomous Finance Crew

Assemble a team of agents to manage your company's finances. A 'Collector' agent can run daily, using `search_invoices` to find all overdue invoices. It passes this list to a 'Communicator' agent, which uses `search_contacts` to find the right person to notify. This crew works autonomously in the background. You can even add a 'Reporting' agent that compiles a summary of its actions and sends it to you. This is how you scale financial oversight without hiring more people. This MCP Server gives them the tools they need.

Automate Project Management and Tasking

A 'Project Manager' crew can take over the administrative burden of running projects. For example, a 'Scout' agent can monitor incoming support requests. When a new one arrives, it hands off to a 'Planner' agent that uses the `create_project` or `create_task` tool to formally log the work in Moxie. An 'Assigner' agent can then use `list_users` to find an available team member and assign the task. Each agent in the crew has a specific role, and you can use `tool_filter` to ensure they only have access to the Moxie tools they absolutely need.

Run Proactive Client Health Monitoring

Don't wait for clients to complain. Set up a 'Client Health' crew to proactively monitor accounts. One agent can periodically run `search_projects` to check for stalled work or scope creep. Another can use `search_invoices` to check for consistently late payments. If the crew detects a problem, it can use the `create_ticket` tool to automatically open an internal ticket for an account manager to investigate. This turns your operations from reactive to proactive.

Setup guide

Set up Moxie 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 Moxie tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can create a 'Client Onboarding' crew. The first agent could use `create_client`, a second agent could use its output to call `create_project`, and a third could use `create_task` to set up the initial project milestones. They work together in a sequence to complete the process.

Yes. When you configure the MCP server in CrewAI, you can use the `tool_filter` argument. This lets you grant the `create_invoice` tool to your 'Finance' agent but not your 'Project' agent, following the principle of least privilege.

Definitely. You would create an agent and configure its MCP tools to only include `list_users`. This is useful for a 'Directory' agent that can be queried by other agents to find contact information for people in your workspace.

It's straightforward. You pass the unique Vinkius URL for your Moxie server into the `mcps` list when defining your Agent. CrewAI handles the connection and makes the tools available to the agent.

The crew will access the data needed for its job, like client names, project data, invoice details, and time entries. The key to security with CrewAI is using `tool_filter` to strictly limit each agent's permissions. Your 'invoicing' agent shouldn't have access to `create_project`, and Vinkius ensures the entire MCP server environment is sandboxed and private to you.

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