MCP server for token-metrics providing access to Token Metrics API data including token information, OHLCV data, technical indicators, and trading strategy analysis
Server has 14 tools with basic descriptions and input schemas present. However, most descriptions are under 100 chars and lack actionable context for LLM selection. Parameter descriptions are minimal or missing entirely. No output schemas documented. Error handling is absent, tools will fail silently or return raw exceptions. Tool naming is verb-first (good), but many tools are generic list/cache operations with overlapping responsibilities. No pagination support despite returning potentially large lists. Security: API keys are environment-injected (good), but no permission gates or audit trails. Overall: functional but below production baseline.
Fetch and cache all available lists from Token Metrics API. Saves them as CSV files in the 'lists' directory.
Get the list of all tokens for AI reports. Endpoint: /v2/ai-reports-tokens
Get the list of all blockchains supported by Token Metrics. Endpoint: /v2/blockchains
Get the status of all cache files
Get the list of all token categories available in Token Metrics. Endpoint: /v2/categories
Get the list of all token IDs, names, and symbols from Token Metrics. Endpoint: /v2/coins
Get daily Open-High-Low-Close-Volume data for specified tokens. Requires API key to be set in TOKEN_METRICS_API_KEY environment variable.
No output schemas documented. LLMs cannot infer what fields to expect from tool responses, forcing them to guess at downstream field names and risk broken tool chains.
List tools (get_coins_list, get_categories_list, etc.) lack pagination parameters (limit, offset, page_size) and return unbounded results. Large result sets will exhaust context windows and degrade LLM reasoning.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 59 | <=2025-11-25 | v2 |
Get Exponential Moving Averages (EMAs) for a specified token and timeframe using vectorbt.
Get the list of all exchanges tracked by Token Metrics. Endpoint: /v2/exchanges
Get hourly Open-High-Low-Close-Volume data for specified tokens. Requires API key to be set in TOKEN_METRICS_API_KEY environment variable.
Get the list of available technical indicators. Endpoint: /v2/technical-indicators
Get detailed information for a specific token by symbol Uses the coins endpoint and filters by symbol
Get detailed information for specific tokens using premium API. Requires API key to be set in TOKEN_METRICS_API_KEY environment variable.
Invalidate and refresh all cached data from the API. Forces a fresh fetch of all data regardless of cache age.
No error handling or recovery guidance. Tools will fail with raw exceptions or API errors. LLMs receive no actionable guidance on what to do next (retry, ask user, try alternative tool).
Descriptions for list tools are generic and under 100 chars. They do not explain WHEN to call each tool or how they differ from each other. LLMs may conflate get_coins_list with get_tokens_info.
No permission gates or audit trails. Destructive tools (cache_all_lists, invalidate_cache) can be called without authorization checks. No logging of who called what, when, or with what result.