How to Use the Mav MCP in CrewAI

Q: How do CrewAI agents share data when calling Mav tools?

The researcher agent gets lead details via getlead and writes them to the crew's shared memory. The outreach agent then reads this memory to execute the next MCP step.

Q: How do I update a lead's status across multiple agents?

Any agent in the crew can call updatelead to sync progress. The updated status is immediately visible to all other agents in the execution chain.

Run autonomous agent teams that qualify leads and manage SMS playbooks using Mav and CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mav MCP to CrewAI

Create your Vinkius account to connect Mav 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 Mav with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent SMS Qualification Teams

The `list_leads` tool allows your CrewAI researcher agent to scan your active pipeline for prospects who haven't been contacted yet. Once found, the researcher hands the data over to the outreach agent, who uses this MCP Server to kick off the text conversation. This division of labor keeps your operations running 24/7 without human intervention. Each agent focuses on one specific task, making the entire qualification funnel run like clockwork.

Automated Lead Progress Audits

The `list_activities` tool provides your moderator agent with a complete log of recent SMS events to analyze campaign performance. The agent can spot bottlenecks, like leads getting stuck on a specific question, and flag them for review. This gives you an autonomous feedback loop. Your crew monitors its own performance and keeps your SMS outreach highly effective.

Intelligent Playbook Assignment

The `list_playbooks` tool lets your coordinator agent review all available outreach sequences before launching a campaign. The agent matches the lead's profile with the best playbook, executing the MCP tool directly. This prevents generic, spammy outreach. Your crew acts like a smart sales assistant, selecting the perfect messaging angle for every single lead.

Setup guide

Set up Mav 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 Mav tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The researcher agent gets lead details via `get_lead` and writes them to the crew's shared memory. The outreach agent then reads this memory to execute the next MCP step.

Yes, you can restrict tools so only your manager agent can call `stop_playbook` while your SDR agent uses `create_lead`. This keeps your multi-agent team organized and secure.

When a lead texts 'stop,' your monitor agent detects the event in `list_activities` and instructs the compliance agent to call the MCP tool.

Any agent in the crew can call `update_lead` to sync progress. The updated status is immediately visible to all other agents in the execution chain.

All sensitive lead phone numbers and opt-out statuses are handled within an isolated, zero-trust MCP execution environment. Data is encrypted in transit and never stored outside your local setup.

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