context-usage-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_context_usageA | Reports the current session's raw token usage, read directly from the host's own session transcript/rollout (auto-detected: Claude Code or OpenAI Codex CLI). Returns raw counts only — context_tokens (input + cache_creation + cache_read) plus a full breakdown and session metadata (session_id, model, timestamp) — with no percentage or context-window detection. May be unavailable early in a session before the first model response; then it returns { available: false, reason } instead of failing. |
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 1 tool
With only one tool, there is no possibility of ambiguity or misselection. The tool's purpose is clearly defined and distinct by default.
The single tool name 'get_context_usage' follows a clear verb_noun pattern. Consistency is trivially maintained as there are no other tools to contrast with.
The server has only one tool, which feels thin for a typical server but is arguably sufficient for its narrow purpose. It is not trivial, but the count is on the lower end of the acceptable range.
The tool covers the core raw token usage reporting, but it explicitly lacks percentage or context-window detection, leaving a notable gap for users who need derived insights. The domain is narrowly focused, but the surface is somewhat incomplete.