codexwatch
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.
Answers questions about this user's OpenAI Codex usage from their local session logs: tokens, API-equivalent dollars, plan limits and budgets.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| usage_summaryB | Codex token usage and its API-equivalent dollar value for a period: totals, cache hit rate, and the top models and projects. Dollar figures are estimates at OpenAI API prices; tokens of models with no published price are counted separately. |
| plan_limitsB | Where the ChatGPT plan's Codex limits stand now: each window's percent used, reset time, burn rate per hour and projected time it fills, read from the newest session log. With codexhop installed, also every saved account's last reading and the account with the most 5-hour room. |
| quota_forensicsA | What each percentage point of the plan cost in API-equivalent dollars and tokens, per window and per day, plus rises in a window that the local logs cannot explain (usage from another machine, ChatGPT itself or cloud tasks, or a metering change). |
| sessionsB | The most recent Codex sessions with title, project, models, turns, tokens and dollar value. |
| dailyB | Tokens and API-equivalent dollars per local day, oldest first, with empty days included. |
| budget_statusB | The user's codexwatch budgets (dollar, token or plan-window caps) with how much of each is used and whether it is near or over its limit. |
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
Each tool targets a distinct slice of Codex usage monitoring: period summary, plan-window status, forensic cost-per-point analysis, session listing, daily time series, and budget status. There is minor overlap between usage_summary, daily, and quota_forensics since all report token/dollar usage, but their descriptions clarify the different granularities and purposes.
All tools use lowercase snake_case and are noun-based metric/resource names, which is predictable. Minor deviation: some are single words (sessions, daily) while others are compound noun phrases (usage_summary, plan_limits), but the style remains consistent overall.
Six tools is well-scoped for a read-only Codex usage and budget monitoring server. Each tool earns its place by covering a different analytical view without excessive granularity.
The surface covers summaries, daily breakdowns, sessions, plan limits, forensic cost analysis, and budget status, giving strong read coverage of the monitoring domain. A minor gap is the absence of tools to create or edit budgets (only status is exposed), but agents can work around this if budgets are configured elsewhere.