How to Use the kvCORE MCP in Claude Code

Q: How do I configure the kvCORE MCP Server for Claude Code?

Run claude mcp add --transport http kvcore-mcp -- . Make sure all flags come before the server name. Verify the connection by running claude mcp list in your terminal.

Q: Can Claude Code automate kvCORE lead searches?

Yes. You can trigger headless scripts that use searchkvcoreleads to find specific contacts. It returns the lead IDs and basic contact info directly to standard output.

Q: How does Claude Code handle kvCORE marketing campaigns?

It calls listmarketingcampaigns to pull the active campaign data. You can pipe this output into jq or another command-line tool to filter the results.

Q: Is it possible to update lead statuses from the CLI?

You just pass the new data as a JSON string to updateleadinfo. Your terminal agent handles the payload delivery and confirms the update.

Manage your real estate pipeline from the terminal. Claude Code executes kvCORE operations headlessly for CI/CD and cron jobs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect kvCORE MCP to Claude Code

Create your Vinkius account to connect kvCORE 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 kvCORE with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script lead updates with Claude Code

This server connects your terminal directly to your real estate database. Real estate operations belong in automated pipelines, not clunky web interfaces. You can pipe a CSV of new contacts directly into your terminal. Your CLI agent reads the file and runs `search_kvcore_leads` to check for duplicates. If a match exists, it executes `update_lead_info` to refresh the phone number or status. It handles the JSON formatting and API calls entirely in the background. You just get the success output in your shell.

Run headless property audits via MCP Server

Checking inventory status shouldn't require logging into a dashboard. Set up a cron job that triggers your terminal agent every morning. It runs `list_property_listings` to pull the active metadata via this MCP Server. Then it hits `get_listing_details` for any properties flagged for review. The agent compiles the data and pipes it to your Slack webhook or a local log file. Zero manual intervention is required.

Automate agent task reporting

Extracting daily schedules is tedious. You can write a bash script that tells your CLI tool to fetch the daily workload. It calls `get_agent_profile` and `list_agent_tasks` to map out the pending calls. The script can then cross-reference those tasks by calling `list_lead_activity`. Finally, it uses `create_lead_note` to log the daily audit. Everything runs headlessly in your SSH session or Docker container.

Setup guide

Set up kvCORE 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 kvcore-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http kvcore-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 kvCORE 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": {
    "kvcore-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 kvCORE. 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 kvCORE 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 kvCORE MCP in Claude Code

Run `claude mcp add --transport http kvcore-mcp -- `. Make sure all flags come before the server name. Verify the connection by running `claude mcp list` in your terminal.

Yes. You can trigger headless scripts that use `search_kvcore_leads` to find specific contacts. It returns the lead IDs and basic contact info directly to standard output.

It calls `list_marketing_campaigns` to pull the active campaign data. You can pipe this output into jq or another command-line tool to filter the results.

You just pass the new data as a JSON string to `update_lead_info`. Your terminal agent handles the payload delivery and confirms the update.

The connection relies on a secure, stateless execution model. When your cron job pulls property listings or agent profiles, the data routes through a V8 Isolate Sandbox and is destroyed immediately after the terminal session closes.

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