How to Use the AgentFire MCP in VS Code Copilot

Q: How do I configure the AgentFire MCP Server for my team in VS Code Copilot?

Create a .vscode/mcp.json file in your project's root directory. Add the AgentFire server configuration to it, then commit the file to your Git repository. Every team member who pulls the repo will have Copilot configured automatically.

Give your entire team access to AgentFire data inside VS Code with GitHub Copilot.

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 VS Code Copilot

Create your Vinkius account to connect AgentFire to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Onboard your team with shared API access

Add this MCP Server to your project's `.vscode/mcp.json` and commit it. Now, everyone on your team gets instant access to the AgentFire API through Copilot. A new developer can ask Copilot about a property or a lead without needing separate credentials or leaving VS Code. This shared configuration means your team is consistent. Every developer builds against the same live data source, cutting down on setup friction. It's a managed, secure way to connect your whole team to your business data.

Build and test with live data

Copilot's agent can use tools like `get_listing` and `get_lead` to bring real data into your development cycle. As you're writing a new feature, tell Copilot to “grab the details for lead ID 123” and paste the JSON response as a test fixture. Your tests become more realistic than when you use stale, hard-coded data. You can also create test records on the fly. Tell Copilot, “create a new lead with this email” using the `create_lead` tool. This gives you a fresh record to test update and delete functions against, all from your editor.

A reliable AgentFire MCP Server for your team

This managed server connects GitHub Copilot to your AgentFire account. It gives your agent a specific set of commands to manage properties and leads. You can search for listings with `search_listings` or get your own user info with `get_profile`. Because Vinkius hosts and manages the MCP Server, you don't deal with hosting or maintenance. Just add the configuration to your project, and your team's Copilot can immediately start working with AgentFire. You can always run `check_agentfire_status` to confirm the connection.

Setup guide

Set up AgentFire MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the AgentFire MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the AgentFire tools listed. Try asking: "List my recent AgentFire transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a `.vscode/mcp.json` file in your project's root directory. Add the AgentFire server configuration to it, then commit the file to your Git repository. Every team member who pulls the repo will have Copilot configured automatically.

Yes. In the Copilot chat, you can ask, "@workspace find listings in AgentFire near Austin, TX." Copilot will use the `search_listings` tool from this MCP Server to get the answer.

Open the Copilot chat and type, "@workspace use the AgentFire tool to create a lead with the email test@example.com." Copilot will execute the `create_lead` command for you.

Yes, this server works with any version of GitHub Copilot that supports agent chat in VS Code 1.96 or newer. The configuration can be managed and deployed by your IT department.

This server connects to AgentFire through Vinkius's zero-trust infrastructure. Your lead and property data is never stored or logged; it's streamed through an ephemeral environment only to fulfill your agent's request. Access is controlled by your team's Vinkius token.

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