How to Use the Assembly MCP in CrewAI

Q: Can CrewAI agents pass Assembly workspace data to each other?

Yes. An agent can pull a directory using listworkspaces and store the result in shared memory. The next agent in the sequence will read that data and act on it.

Q: How do I restrict which Assembly tools my CrewAI team can use?

Use the toolfilter parameter during setup. You can allow an agent to use listnotes while blocking it from seeing user details.

Deploy autonomous CrewAI teams to manage your Assembly environment. Assign specialized agents to monitor workspaces and analyze notes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Assembly MCP to CrewAI

Create your Vinkius account to connect Assembly 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 Assembly with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Assembly Tasks to CrewAI

You don't need to manually check every project update. Give one agent the job of monitoring active projects by running `list_workspaces` on a loop. When it finds a new entry, it hands the ID off to an analyst agent. The analyst then runs `get_workspace` and pulls all related documentation using `list_notes`. Because the agents share memory, they pass context back and forth without losing details. They work down the list autonomously.

Map Organizations Automatically

Researching corporate structures takes hours of manual clicking. You can configure a researcher role to execute tools from this MCP server, like `list_companies`, to map out every entity in your system. It builds a complete overview without human intervention. A secondary agent can take that list and drill into specific profiles using `get_company` and `list_clients`. You just set the hierarchical execution order and let the crew compile the final report.

Audit User Permissions

Keeping track of who has access to what is tedious. You can build a security crew that periodically runs `list_users` to pull the active roster. The moderator agent reviews the output against your internal policies. If something looks wrong, the agent can flag the profile using `get_user` for a detailed review. The whole process runs through the Vinkius infrastructure, keeping the connection secure and isolated.

Setup guide

Set up Assembly 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 Assembly tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius URL directly into the mcps array when defining an agent. For more granular control, use MCPServerHTTP from crewai.mcp to filter exactly which tools the agent can see.

Yes. An agent can pull a directory using `list_workspaces` and store the result in shared memory. The next agent in the sequence will read that data and act on it.

Use the tool_filter parameter during setup. You can allow an agent to use `list_notes` while blocking it from seeing user details.

The server simply provides the tools. Your manager agent evaluates the goal and delegates specific tasks, like running `get_company`, to the right subordinate based on your configuration.

Vinkius processes every tool call inside a strict, single-use V8 sandbox. When your agent runs `list_clients`, the data passes through an ephemeral environment that gets completely destroyed after the response ships.

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