How to Use the Close MCP in CrewAI

Q: How can I give different Close tools to different agents in CrewAI?

When you define your Agent in CrewAI, you can pass a specific list of tools. To give one agent access to createlead and another access to listleads, you would load the MCP Server tools and filter them before assigning them to each agent.

Q: Can a CrewAI agent create a new lead in our Close CRM?

Absolutely. You just need to assign an agent the createlead tool from this MCP server. Then, as part of a task, that agent can execute the tool to add a new lead to your Close account.

Q: Can I see which agent performed an action in Close with CrewAI?

The getcurrentuser tool can help with that. You can have an agent use this tool at the start of its task to log which API key (representing a user or service account) is performing the actions. This is useful for auditing your crew's work.

Deploy an autonomous sales team for Close. Use CrewAI to have multiple agents collaborate on managing your leads and opportunities.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Close MCP to CrewAI

Create your Vinkius account to connect Close 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 Close with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Pipeline Monitoring Crew

Assign a crew of agents to watch your sales pipeline 24/7. One agent can act as a spotter, looking for problems, while another acts as an analyst, digging into the details. It's autonomous oversight for your sales process. Give your 'Monitor' agent the `list_opportunities` tool to scan for deals that haven't been updated recently. When it finds one, it passes the lead ID to an 'Analyst' agent. That agent then uses `get_lead_details` to pull all available information and flag it for a human sales rep.

Automate Lead Qualification with an Agent Crew

Set up a crew to handle new leads as they come in. This frees up your sales team to focus on selling, not data entry. One agent can create the lead, and another can verify it's been processed correctly. An 'Ingestion' agent's only job is to receive data and use the `create_lead` tool. Once done, a 'QA' agent can use `list_leads` with a filter to confirm the new lead appears in Close as expected. This separation of duties makes your automation cleaner.

Build a CrewAI Sales Reporting Team

Let a team of agents prepare your weekly sales reports. An 'Extractor' agent can pull all the raw numbers, and an 'Analyst' agent can process them. The whole process runs without you lifting a finger. This MCP Server gives your agents the tools they need. The Extractor agent would use `list_leads` and `list_opportunities` to get everything from Close. It then hands that raw data to the Analyst agent, which can summarize trends, identify top performers, and format a report.

Setup guide

Set up Close 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 Close tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

When you define your `Agent` in CrewAI, you can pass a specific list of tools. To give one agent access to `create_lead` and another access to `list_leads`, you would load the MCP Server tools and filter them before assigning them to each agent.

Absolutely. You just need to assign an agent the `create_lead` tool from this MCP server. Then, as part of a task, that agent can execute the tool to add a new lead to your Close account.

You pass the Vinkius MCP URL, which contains your auth token, into the `mcps` parameter when creating your CrewAI agent. CrewAI handles the connection, so your agents are automatically authenticated to perform actions in Close.

The `get_current_user` tool can help with that. You can have an agent use this tool at the start of its task to log which API key (representing a user or service account) is performing the actions. This is useful for auditing your crew's work.

Yes. Your crew's requests for lead and opportunity data are routed through Vinkius's zero-trust infrastructure. The MCP server that processes the request is isolated and ephemeral, meaning it's created just for the request and destroyed immediately after. Your data is not logged or stored.

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