How to Use the AgentFire MCP in Cursor

Q: How does the AgentFire MCP Server work with Cursor's agent mode?

Once you've configured the MCP Server in your mcp.json, Cursor's agent can see and use the AgentFire tools. When you ask it to do something related to leads or listings, it will automatically invoke the right tool to get live data.

Q: Is there a way to check if the AgentFire connection is working in Cursor?

Yes, just ask the agent to run the checkagentfirestatus tool. It will ping the AgentFire API and tell you if the connection is live.

Inject live AgentFire listings and lead data directly into your code with Cursor's agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentFire MCP to Cursor

Create your Vinkius account to connect AgentFire 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 AgentFire with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate code with real listing data

Cursor's agent uses `search_listings` and `get_listing` to pull actual property data into your editor. Tell the agent, “write a Python script to fetch the 5 most expensive listings and print their addresses.” It calls the tools and generates working code populated with real-time results from your AgentFire account. No more mock data. This is a huge time-saver for building front-end components or backend API clients. You see exactly what the payload looks like from the AgentFire MCP Server and can code against it immediately, all without leaving Cursor.

Script your lead management workflow

Automate your lead pipeline by telling Cursor's agent to use `create_lead` and `update_lead`. You can say, “draft a function that takes an email and name and creates a new lead in AgentFire.” The agent will call the tool, see the required parameters, and write the function for you. It works the same way for getting data. Ask the agent to use `get_lead` or `list_leads` to build functions that pull contact information. It sees the API response and writes code that correctly handles the data structure, saving you a trip to the API docs.

Connect your codebase to AgentFire

This MCP Server gives your Cursor agent direct access to your real estate data. It exposes 10 tools for managing leads, listings, and contacts. Just configure the server in your `mcp.json` file, and you can start telling the agent to interact with the AgentFire API. You can even build internal tools faster by asking the agent to get your own user info with `get_profile` or pull all your contacts with `list_contacts`. It's a fast way to build and test code that works with your live AgentFire environment.

Setup guide

Set up AgentFire 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 AgentFire 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 AgentFire transactions." If the MCP tools are loaded correctly, Cursor will call the AgentFire tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "agentfire-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 AgentFire. 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 AgentFire 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 AgentFire MCP in Cursor

Once you've configured the MCP Server in your `mcp.json`, Cursor's agent can see and use the AgentFire tools. When you ask it to do something related to leads or listings, it will automatically invoke the right tool to get live data.

Absolutely. Just instruct the agent: "Write a script that uses the `create_lead` tool to add a new lead." The agent will generate the code, importing any necessary libraries and handling the API call for you.

You can access anything the tools expose: leads, contacts, and property listings. You can list all records, get a specific record by its ID, or search for listings based on criteria.

Yes, just ask the agent to run the `check_agentfire_status` tool. It will ping the AgentFire API and tell you if the connection is live.

All requests are proxied through a secure Vinkius environment that doesn't log or store your data. The server handles your lead and property listing details only for the duration of the API call. Nothing is kept.

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