llm-token-tracker
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| track_usageC | Track token usage for an AI API call |
| get_current_sessionC | Get current session usage with intuitive format (remaining, used, input/output tokens, cost) |
| get_usageC | Get usage summary |
| compare_costsC | Compare costs between models |
| clear_usageC | Clear usage data |
| get_exchange_rateB | Get current USD to KRW exchange rate with cache info |
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 6 tools
Most tools have distinct purposes, but get_current_session and get_usage could be confused as both retrieve usage data, though their descriptions differentiate them slightly (session-specific vs. summary). The other tools (clear_usage, compare_costs, get_exchange_rate, track_usage) are clearly distinct.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., clear_usage, compare_costs, get_current_session). There are no deviations in naming style, making them predictable and readable.
With 6 tools, the count is well-scoped for tracking LLM token usage and costs. Each tool serves a specific function in this domain, such as tracking, retrieving, clearing, and comparing data, without being excessive or insufficient.
The toolset covers core operations like tracking, retrieving, and clearing usage, but lacks update or delete capabilities for specific entries, which might be needed for error correction. The inclusion of get_exchange_rate is useful but slightly tangential to the main purpose.