How to Use the Copilot CRM (Assembly) MCP in CrewAI

Q: How do I assign Copilot CRM (Assembly) MCP Server tools to specific CrewAI agents?

You pass the server URL to the mcps list when defining your agents. For example, you can give your billing agent access to listinvoices while restricting your support agent to listportalmessages.

Q: Can I filter which tools my CrewAI team can access?

Yes, you can use the MCPServerHTTP class from crewai.mcp and specify a toolfilter to only expose tools like listclients while hiding sensitive ones.

Q: Is my client contact information safe when running autonomous CrewAI agents?

Absolutely. All interactions with getclientdetails and listclients run through an ephemeral, zero-trust V8 sandbox. Your customer names, emails, and phone numbers are never stored outside your portal.

Deploy specialized CrewAI agent teams to coordinate client communications and manage your Copilot CRM (Assembly) data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Copilot CRM (Assembly) MCP to CrewAI

Create your Vinkius account to connect Copilot CRM (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 Copilot CRM (Assembly) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous portal management with CrewAI

The `list_clients` and `list_companies` tools allow your CrewAI agent teams to cross-reference corporate data. You can set up a researcher agent to identify unlinked accounts and a coordinator agent to clean up the records. By using `update_client`, the coordinator agent can automatically link orphaned contacts to their parent companies. This multi-agent setup ensures your portal data stays organized without human supervision.

Automated portal inbox moderation

This MCP Server exposes `list_portal_messages` to let your CrewAI support team monitor client inquiries. A triage agent reads the incoming messages, while a separate responder agent drafts replies or escalates urgent issues. If an inquiry requires billing context, the triage agent can invoke `list_invoices` to pull current payment statuses. This shared memory model ensures all agents have the context they need to resolve issues.

Intake form processing and file organization

We use the `list_forms` and `list_files` tools to coordinate your document-heavy operations. A dedicated intake agent monitors form submissions, while a filing agent organizes uploaded documents in the portal. The filing agent can query `get_client_details` to ensure files are associated with the correct user profile. This keeps your client portals clean and your documents properly categorized.

Setup guide

Set up Copilot CRM (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 Copilot CRM (Assembly) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the server URL to the `mcps` list when defining your agents. For example, you can give your billing agent access to `list_invoices` while restricting your support agent to `list_portal_messages`.

Yes, they share memory during an execution run. One agent can pull profile details with `get_client_details` and pass that structured data to another agent responsible for running `update_client`.

The server handles concurrent requests smoothly. If your triage agent and billing agent call `list_portal_messages` and `list_invoices` at the same time, Vinkius processes both calls in parallel.

Yes, you can use the `MCPServerHTTP` class from `crewai.mcp` and specify a `tool_filter` to only expose tools like `list_clients` while hiding sensitive ones.

Absolutely. All interactions with `get_client_details` and `list_clients` run through an ephemeral, zero-trust V8 sandbox. Your customer names, emails, and phone numbers are never stored outside your portal.

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