How to Use the AgentFire MCP in Claude Code

Q: How can I use Claude Code in a script to create a new lead in AgentFire?

You can pipe the data directly. For instance, echo '{"email":"test@test.com"}' claude mcp agentfire createlead. It's designed for scripting and automation.

Q: What is the command to connect Claude Code to the AgentFire MCP server?

Run claude mcp add agentfire -- . You can then verify the connection is active by running claude mcp list.

Q: Can I pipe JSON from another tool to Claude Code to update AgentFire listings?

Yes. As long as the JSON matches the schema for the updatelead or updatelisting tool, you can pipe it directly from jq, curl, or any other command-line tool.

Automate AgentFire tasks and build real estate data pipelines right from your terminal with Claude Code.

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 Claude Code

Create your Vinkius account to connect AgentFire to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Lead Management in Scripts

This is built for the command line. You can pipe data directly into AgentFire. For example, `cat new_leads.csv | claude mcp agentfire create_lead`. Claude Code processes each line and creates the leads for you. It's perfect for building shell scripts to sync leads from another source. Use `update_lead` for nightly updates or `list_leads` to generate daily reports, all completely headless.

Run Real Estate Checks in CI/CD

Add this MCP Server to your GitHub Actions or other CI/CD pipelines. A common use is running a daily job to monitor your listings. Set up a simple cron job that runs `claude mcp agentfire search_listings --criteria 'status=new'` and pipes the output to a Slack notification script. You can automate your team's entire workflow.

Quick Data Lookups from the CLI

Forget logging into a web UI. Just open a terminal and run `claude mcp agentfire get_listing --id 456` to pull details on a property instantly. You can also check your own permissions with `get_profile` or test the API connection with `check_agentfire_status`. It gives you raw, direct access without writing a line of integration code.

Setup guide

Set up AgentFire MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see agentfire-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest AgentFire transactions." It will automatically discover and invoke the available AgentFire tools.

Terminal

claude mcp add --transport http agentfire-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the AgentFire MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "agentfire-mcp": {
      "type": "url",
      "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 Claude Code

You can pipe the data directly. For instance, `echo '{"email":"test@test.com"}' | claude mcp agentfire create_lead`. It's designed for scripting and automation.

Yes, that's a primary use case. Just create a cron job that executes `claude mcp agentfire list_leads` and pipes the output to whatever notification or processing script you need.

Run `claude mcp add agentfire -- `. You can then verify the connection is active by running `claude mcp list`.

Yes. As long as the JSON matches the schema for the `update_lead` or `update_listing` tool, you can pipe it directly from `jq`, `curl`, or any other command-line tool.

The data is only ever in-flight. When your CI/CD job runs, your AgentFire lead and contact data is processed in a dedicated V8 isolate sandbox that is destroyed after the request completes. Nothing is logged or persisted.

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