Glassnode MCP Server
A guide to using Glassnode's Model Context Protocol (MCP) server for AI agents.
The Glassnode MCP Server is currently in beta, and its tools are subject to change. Although this MCP server produces accurate data, it is possible that it could be misinterpreted by the LLM you are using.
Overview
Crypto on-chain metrics and market intelligence for AI agents.
A Model Context Protocol (MCP) server providing access to Glassnode's API. The server enables AI agents to access on-chain metrics, market data, and analytics.
For detailed information about the API and available data:
Features
Asset and metrics discovery
Metric metadata retrieval
Single and bulk data retrieval
Tools
The server provides seven tools for accessing Glassnode data:
get_assets_list: Get a list of all cryptocurrencies and tokens supported by Glassnodeget_metrics_list: Get a catalog of all available metrics and their paths, optionally filtered by categoryget_asset_metrics: Get metrics available for a specific assetget_metric_metadata: Get detailed information about a specific metric's structure and parametersfetch_metric: Fetch data (max 30d history) for a specific metric with customizable parametersfetch_bulk_metrics: Fetch data (max 30d history) for multiple assets simultaneously in a single request
Quick Setup
Claude
To add the Glassnode MCP server using Claude Connectors:
Open Claude desktop or web app
Go to
Settings > Connectors > Add custom connector(https://claude.ai/settings/connectors)Enter the URL:
https://mcp.glassnode.comClick
AddClaude will automatically configure the connection
For more advanced configuration, read below.
Claude Desktop Configuration
Add the following to your claude_desktop_config.json:
Or using your API key, to remove 30d time range limits:
Claude CLI Quick Add
Restart your Claude client after updating configs.
Other MCP clients
Add the following configuration to your mcp_config.json:
Example Prompts
Get an overview of the MCP tools.
Simple prompts:
More advanced:
Last updated