How to Use the Kava Explorer MCP in Claude Code

Q: How do I configure Kava Explorer for Claude Code?

Run claude mcp add --transport http kava-explorer -- in your terminal. Ensure you pass your Subscan API key via the appropriate header or environment flag. Verify the installation with claude mcp list.

Pipe Kava blockchain data directly into your terminal. Claude Code executes headless Subscan queries for fast, command-line chain analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kava Explorer MCP to Claude Code

Create your Vinkius account to connect Kava Explorer 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 Kava Explorer with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Terminal-Native Account Audits

The `get_account_info` and `get_account_token` tools pull Kava wallet balances straight into your shell session. You ask Claude Code to verify a deployment address. It runs the query, parses the JSON response, and prints the exact token amounts to your standard output. This MCP Server handles complex historical data just as easily. You can script a command to check `get_account_reward_slash` for a list of validators. The CLI agent grabs the data, formats it into a neat terminal table, and exits.

Headless Transaction Inspection

The `get_extrinsic` tool retrieves the exact payload of any Kava transaction without opening a browser. When a CI pipeline fails due to a bad contract call, you trigger Claude Code to inspect the hash. It returns the exact error code from the chain. The MCP integration lets you batch process network activity. The agent uses `list_extrinsics` and `list_events` to scan recent blocks for specific method calls. It filters the noise and pipes the relevant events into your local log files.

Validator Mapping in Claude Code

The `list_validators` and `get_validator` tools give your terminal agent direct access to Kava consensus data. You can set up a cron job where the agent checks node uptime every hour. It queries the active set and alerts you if a specific node drops blocks. Block monitoring works the same way. The agent fires `list_blocks` to check chain progression, then uses `get_block` to extract specific header details. It handles all the pagination behind the scenes, delivering clean data to your command line.

Setup guide

Set up Kava Explorer 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 kava-explorer-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http kava-explorer-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 Kava Explorer 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": {
    "kava-explorer-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 Kava Explorer. 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 Kava Explorer 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 Kava Explorer MCP in Claude Code

Run `claude mcp add --transport http kava-explorer -- ` in your terminal. Ensure you pass your Subscan API key via the appropriate header or environment flag. Verify the installation with `claude mcp list`.

Yes. You can run the CLI agent in headless mode within a GitHub Action. It will execute queries against the chain to verify deployment transactions before allowing a pipeline to proceed.

The tools return raw JSON, but the agent automatically parses it. You can tell the CLI to output the data as a clean table, a markdown summary, or pipe it into `jq` for further processing.

The agent catches the HTTP error and prints the exact Subscan failure reason to `stderr`. It will often suggest a fix, like adjusting your pagination parameters or checking your API key.

This integration strictly reads public chain data such as block hashes, event logs, and token transfers. The terminal client manages the connection locally. No proprietary codebase data is sent to the Subscan API, ensuring your internal logic remains isolated from the public ledger queries.

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