A Model Context Protocol server that provides resources and tools for interacting with the Glassnode API.
Server has 6 tools with basic descriptions and some parameter documentation, but significant gaps in schema completeness, parameter descriptions, and error handling. Tools 1-2 read from static JSON files (assets.json, metrics.json) with no visible error recovery guidance. Tools 3-6 have descriptions but lack comprehensive parameter validation and output schema documentation. No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite all being READ_ONLY. Parameter descriptions are present but often generic (e.g., 'Optional start date as Unix timestamp' without format/range constraints). Output schemas are not documented, LLMs cannot predict response structure. Error handling returns JSON error objects but provides no recovery guidance or actionable next steps.
Fetch data for a metric using Glassnode's bulk endpoint. Use this when you need to fetch data for multiple assets. IMPORTANT - First call the resource get_metrics_list() to get all available metrics. Verify that '{metric_path}' is a valid metric path. If not, find the closest matching metric path from the list. If the user provides a relative time range (e.g., "lastest", "past week", "last 24 hours", "last 30 days", "past 12 months", "past 1 year"), the agent must convert it into an absolute time range using the current UTC time (e.g., get current UTC time, subtract 7 days), and then pass the result as ISO 8601 `since` parameter. If not specifically desired by the user, `until` can be ommitted. The data returned will extend to the most recent available datapoint.
Fetch data for a specific metric. IMPORTANT - First call the resource get_metrics_list() to get all available metrics. Verify that '{metric_path}' is a valid metric path. If not, find the closest matching metric path from the list. If the user provides a relative time range (e.g., "lastest", "past week", "last 24 hours", "last 30 days", "past 12 months", "past 1 year"), the agent must convert it into an absolute time range using the current UTC time (e.g., get current UTC time, subtract 7 days), and then pass the result as ISO 8601 `since` parameter. If not specifically desired by the user, `until` can be ommitted. The data returned will extend to the most recent available datapoint.
Get a list of available metrics for a specific asset. This resource returns a JSON object containing all metrics that are available for the specified asset. Use this when you need to: - Find which metrics are supported for a specific asset - Filter available metrics by asset before making data requests - Check asset-specific metric availability
No output schemas documented. Tools return JSON strings or Dict but LLMs cannot predict field names, types, or structure. Breaks downstream tool chaining and forces LLMs to parse unstructured output.
Parameter descriptions lack format/range constraints. 'since' and 'until' documented as 'Unix timestamp' but no min/max bounds, no guidance on whether milliseconds or seconds, no examples of valid ranges.
Error handling returns bare JSON error objects with no recovery guidance. E.g., 'File not found' or 'Asset not found', no suggestion to call get_assets_list() first or list available assets.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |
Get a list of all cryptocurrency assets supported by Glassnode API. This resource returns a JSON object containing all available assets and their metadata. Use this when you need to: - Verify if a specific asset is supported - Get the correct asset symbol to use in data fetching tools - Display available assets to users
Get metadata for a specific metric. IMPORTANT - First call the resource get_metrics_list() to get all available metrics. Verify that '{metric_path}' is a valid metric path. If not, find the closest matching metric path from the list.
Get a list of all available metrics and their paths from Glassnode API. IMPORTANT: This resource should be used to retrieve the correct metric paths that are required when calling the data fetching tools (fetch_metric and fetch_bulk_metric). The paths returned by this resource are the exact format needed as the 'path' parameter for those tools. Examples of metric paths you might find: - /market/price_usd_close - /market/price_drawdown_relative - /blockchain/utxo_created_count Use this resource when you need to: - Find the correct path for a specific metric - Discover available metrics and their categories - Validate if a specific metric exists before attempting to fetch data - Display available metrics to users
No tool annotations despite all tools being READ_ONLY. Missing readOnlyHint annotation prevents agents from understanding safety properties and optimizing retry/caching strategies.
Pagination not implemented. fetch_metric and fetch_bulk_metric accept 'limit' but no offset/cursor or total_count in response. Large result sets will blow context window without pagination guidance.