How to Use the Glassnode (On-chain Data) MCP in Claude

Q: How do I query Glassnode (On-chain Data) metrics directly inside Claude Desktop?

Add the server configuration to your local claudedesktopconfig.json file. Once connected, ask Claude Desktop to pull specific metrics like active addresses using the getmetric tool.

Q: Can I analyze multiple tokens at once using Glassnode (On-chain Data) in Claude Desktop?

Yes. Your local agent calls getbulkmetric to enable this MCP Server to gather data across several networks simultaneously. Claude Desktop displays these metrics in a single view for quick comparison.

Q: How do I find the exact metric path name for a query?

Ask your desktop agent to run listmetrics first. It returns the exact string paths needed for tools like getmetricdetails to verify parameter requirements.

Feed institutional on-chain metrics directly to Claude Desktop to spot market shifts before they hit the exchanges.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glassnode (On-chain Data) MCP to Claude Desktop

Create your Vinkius account to connect Glassnode (On-chain Data) to Claude Desktop 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 Glassnode (On-chain Data) with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Token Supply Directly in Claude Desktop

The `list_assets` tool identifies active tokens tracked by Glassnode, letting your local workspace query live network metrics instantly. Your agent parses this list to isolate specific assets, matching your raw watchlists with active on-chain databases. Once you target an asset, `list_metrics` pulls the available data points for that specific contract. Claude Desktop maps out what is trackable, saving you from manual API documentation searches during active trading hours.

Run Point-in-Time Backtests with this MCP Server

This MCP Server uses `get_pit_metric` to retrieve historical, unrevised on-chain data snapshots from specific blocks. Your desktop agent compares these historical states to current market prices, identifying patterns without look-ahead bias skewing your models. Raw feeds prevent backtesting errors, giving your local workspace a reliable way to verify historical trading signals.

Pull Bulk Metrics to Monitor Network Health

Use `get_bulk_metric` to extract network-wide metrics across multiple assets inside your chat window. Claude Desktop formats this multi-asset data into clean tables, highlighting divergence between user growth and token price. The `get_metric` tool pulls specific time-series data like active address counts or exchange inflows. Your agent analyzes these raw numbers to spot sudden liquidity rushes, keeping you ahead of major market moves.

Setup guide

Set up Glassnode (On-chain Data) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Glassnode (On-chain Data) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Glassnode (On-chain Data) MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under glassnode-on-chain-data-mcp.

json

{
  "mcpServers": {
    "glassnode-on-chain-data-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 Glassnode. 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 Glassnode (On-chain Data) 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 Glassnode (On-chain Data) MCP in Claude Desktop

Add the server configuration to your local `claude_desktop_config.json` file. Once connected, ask Claude Desktop to pull specific metrics like active addresses using the `get_metric` tool.

Yes. Your local agent calls `get_bulk_metric` to enable this MCP Server to gather data across several networks simultaneously. Claude Desktop displays these metrics in a single view for quick comparison.

No coding is required. The MCP Server exposes pre-built tools that Claude Desktop runs automatically when you ask questions about on-chain activity.

Ask your desktop agent to run `list_metrics` first. It returns the exact string paths needed for tools like `get_metric_details` to verify parameter requirements.

Vinkius runs the server in an isolated, zero-trust sandbox where your API keys and on-chain queries are encrypted. Your local desktop client communicates through a secure single-token endpoint, keeping your proprietary query patterns completely private.

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