How to Use the Close MCP in Cursor

Q: How do I configure the Close MCP server in Cursor?

Create an mcp.json file in your project root directory. Add the server command and your authentication details under the mcpServers array. Turn on Agent mode in the chat panel to start querying.

Inject real Close API data straight into your Cursor environment to write custom sales dashboards without mocking endpoints.

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 Cursor

Create your Vinkius account to connect Close to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build CRM features with this MCP Server

Calling `list_opportunities` gives Cursor the actual JSON schema of your current sales pipeline. You ask the editor to build a React component for a revenue chart, and it writes the code using real keys and values. There is no need to guess what the payload looks like. Agent mode takes those live responses and maps them directly into your frontend components. You skip the entire process of writing dummy data or checking API documentation. The code works the first time because it was built against the real system.

Write accurate lead ingestion logic

The `create_lead` and `get_lead_details` endpoints allow your AI client to test contact creation scripts while you write them. You can draft a Python script to migrate contacts from an old database. Cursor runs the tool, verifies the lead appears, and adjusts the code if the formatting fails. Testing against a live environment means you catch validation errors immediately. You do not have to wait for a CI pipeline to tell you a phone number field was formatted incorrectly. The agent handles the trial and error in the background.

Automate your daily call sheets

Using `list_crm_tasks` lets Cursor pull your pending follow-ups directly into your terminal or editor pane. You might be building a custom CLI tool to manage your day. The agent fetches the real tasks and helps you write the exact parsing logic required. This MCP implementation turns a static code editor into a live testing ground. You write a function to filter high-priority calls, and the AI immediately proves it works by showing you your actual high-priority contacts. Shipping internal tools happens much faster this way.

Setup guide

Set up Close MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Close MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Close transactions." If the MCP tools are loaded correctly, Cursor will call the Close tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "close-alternative-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Create an `mcp.json` file in your project root directory. Add the server command and your authentication details under the `mcpServers` array. Turn on Agent mode in the chat panel to start querying.

Yes, the agent can write data if you approve the action. It will ask for permission before executing any creation commands. You remain in control of what gets sent.

The system relies on the standard API quotas for your account. Hitting the `get_current_user` endpoint helps verify which workspace you are currently hitting. Keep an eye on your usage if you run large automated scripts.

The connection only reads the code you explicitly share in the chat. It focuses on writing and testing API calls against the remote system. Your local file system remains private unless you attach a file.

Your opportunity values and contact emails never train external models. Vinkius routes the traffic through an ephemeral V8 isolate that drops all memory the second the connection closes. You get the benefits of live data testing without leaking proprietary information.

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