WhyCoinMoves MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_eventsB | Recent published crypto events and measured 5m/1h/24h price reactions. Optional canonical coin id and topic filters. |
| get_coinB | Public coin snapshot, recent source-linked events and observed reactions. Use a canonical id such as bitcoin or ethereum. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
get_events and get_coin both surface events, but the boundary is reasonably clear: one is an event feed with optional filters, the other a per-coin snapshot including events. Minor overlap since a coin-scoped get_events call returns much of what get_coin returns.
Both tools follow the same get_<resource> convention, so the pattern is fully predictable.
Two tools is thin for a data product; a coin listing/discovery endpoint would be natural alongside the per-coin lookup, so the surface feels slightly under-scoped rather than fully earned.
Read-only coverage is coherent (event feed + coin snapshot), but there is no way to enumerate supported coins/topics or paginate/history-browse, which are likely dead ends for an agent exploring the dataset.