How to Use the Tower MCP in CrewAI

Q: If I need to find all tasks, how does CrewAI manage it?

You assign an agent 'Task Auditor' who uses listtasks. This role is specialized for iteration. It finds all tasks within a given project scope and reports them back.

Q: What type of data does Tower touch when using CrewAI?

The server touches sensitive user records (members, teams) and detailed project metadata. The agents interact with this data to perform autonomous operations like task creation or status checks.

Run specialized teams of agents using the CrewAI framework with Tower.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tower MCP to CrewAI

Create your Vinkius account to connect Tower 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 Tower with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Project Discovery

You can assign Agent A to run `list_projects` and gather all available scopes. Then, Agent B takes that list and runs `list_tasks` for each one. This is sequential, specialized work. The entire process happens without needing a human to trigger the second step; the agents collaborate automatically.

Coordinated Team Onboarding

Need to set up a new project? Agent A can use `list_teams` to validate available groups. Then, Agent B uses `list_members` to get all relevant users. Finally, Agent C calls `create_task` with the right team context. The agents manage roles: validation, data gathering, and action execution.

Deep Project Context Analysis

Want a full picture of a project? One agent can run `get_project` for metadata. Another runs `list_doc_folders` to find documentation. A third checks the latest discussions via `list_discussions`. The specialized roles ensure that all necessary data points are gathered and passed into a final summary report.

Setup guide

Set up Tower 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 Tower tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You assign an agent the role of 'Project Manager' and give it access to `list_projects`. This specialized agent runs the tool, gathers all project names, and passes that information along for the next step.

Yes. You can define a 'Task Executor' agent whose sole job is to call `update_task`. This keeps the action separate from discovery, ensuring clean role-based execution.

The agents can pull comprehensive data: they read team roles via `list_members`, project structure via `get_project`, and active discussions using `list_discussions` from the MCP Server.

You assign an agent 'Task Auditor' who uses `list_tasks`. This role is specialized for iteration. It finds all tasks within a given project scope and reports them back.

The server touches sensitive `user records` (members, teams) and detailed `project metadata`. The agents interact with this data to perform autonomous operations like task creation or status checks.

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