How to Use the Assembled MCP in CrewAI

Q: How do I configure CrewAI to use Assembled?

Install the crewaitools package via pip. Pass your Vinkius endpoint directly into the mcps array when defining your Agent. The framework automatically discovers and registers the available tools.

Q: Can I restrict which Assembled tools a CrewAI agent can use?

You can limit access using the MCPServerHTTP class and applying a toolfilter. This ensures a monitoring agent can only read states, while a manager agent has broader access. Role-based specialization works best with scoped permissions.

Deploy specialized autonomous agents to monitor and manage your Assembled support queues using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Assembled MCP to CrewAI

Create your Vinkius account to connect Assembled 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 Assembled with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Agents to Monitor States

The `list_agent_states` tool allows a dedicated monitoring agent to watch your live support floor. This agent constantly reads the current status of every rep to identify who is stuck on a long call or currently idle. You define the role, and the agent executes the observation loop. Coordinating this data requires shared memory across your crew. The monitor agent passes these live states to an analyst agent, which then compares them against planned shifts pulled via `list_schedules`. Autonomous systems identify coverage gaps without any human input.

Analyze Forecasts with CrewAI

Predictive analysis happens when your agents access the `list_forecasts` tool. A specialized forecasting agent can read the upcoming contact volumes and summarize the expected workload for the week. This MCP Server feeds raw numbers into your autonomous pipeline. Evaluating the actual backlog is the next logical step. The agent triggers `list_queues` to see if current ticket counts align with the predicted models. Hierarchical execution ensures the manager agent reviews this comparison before sounding any alarms.

Navigate the Assembled MCP Server

Discovering the organizational structure relies on the `list_teams` tool. Your crew needs to know which pods exist before it can assign specific monitoring tasks. Bootstrapping the connection always starts with a quick `get_account_check` to ensure valid credentials. Digging into individual profiles requires calling `list_users`. When a moderator agent decides to escalate an issue, it finds the right supervisor from this user list. The entire process runs sequentially based on the rules you defined in Python.

Setup guide

Set up Assembled 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 Assembled tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install the `crewai[tools]` package via pip. Pass your Vinkius endpoint directly into the `mcps` array when defining your Agent. The framework automatically discovers and registers the available tools.

You can limit access using the `MCPServerHTTP` class and applying a `tool_filter`. This ensures a monitoring agent can only read states, while a manager agent has broader access. Role-based specialization works best with scoped permissions.

Shared memory allows agents to pass tool outputs to one another. An analyst fetching forecasts will store that context for the moderator agent to use later. The crew collaborates on the same dataset.

You can designate a manager agent to delegate tasks to subordinate agents. The manager might ask one agent to check queues and another to check schedules. It then synthesizes the results into a final report.

Every autonomous request executes within a strict V8 Isolate Sandbox. Live agent states and queue metrics remain ephemeral and vanish once the task completes. The zero-trust model guarantees your data stays isolated from other Vinkius tenants.

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