claude-quota-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLAUDE_QUOTA_SNAPSHOT | No | Override the statusline snapshot location. | |
| CLAUDE_QUOTA_ALLOW_OAUTH_ENDPOINT | No | Set to 1 to permit the undocumented OAuth usage endpoint for the MCP server or hook. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| quota_statusA | Check the agent's own usage limits so long-running work can be planned around resets - e.g. if a window resets soon with usage to spare, front-load heavy work now. Providers: 'claude' (5-hour and weekly percentages from the documented Claude Code statusline snapshot, no credential; the undocumented OAuth usage endpoint only when the host opted in via CLAUDE_QUOTA_ALLOW_OAUTH_ENDPOINT=1; transcript-estimate fallback) and 'codex' (latest server-issued rate-limit snapshot from local Codex rollout logs - exact numbers, freshness = Codex's last activity). Default 'all' reports both. |
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
There is only one tool, so there is no possibility of misselection between tools. Its purpose (report agent usage limits across providers) is clearly stated and self-contained.
A single tool named quota_status in snake_case noun_status form; a lone name cannot conflict with any other convention. It is readable and predictable.
One tool is thin against the 3-15 guideline, but the server's scope is a narrow read-only status probe, so a single entry point is defensible. No tool feels redundant or bolted on.
The domain is quota/limit reporting, and the tool covers both providers with default 'all' plus fallbacks, which is close to a complete surface for a read-only probe. It lacks historical usage or per-model breakdowns, but these are minor gaps an agent can work around.