Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Codex reset tracker: usage-limit reset announcements from @thsottiaux on X. Read-only, no key.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://tokenusage.dev/mcpRun this in your terminal
claude mcp add --transport http codex https://tokenusage.dev/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"codex": {
"url": "https://tokenusage.dev/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"codex": {
"type": "http",
"url": "https://tokenusage.dev/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://tokenusage.dev/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain tokenusage.dev (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.1.0) reached the registry 16 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Zendesk
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Zendesk MCP Pack — tickets, users, organizations via OAuth.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
A hosted, read-only MCP server for OpenAI Codex usage-limit resets, from tokenusage.dev. Ask your agent whether Codex has announced a reset, and it reads the record behind the Codex reset tracker.
https://tokenusage.dev/mcp (Streamable HTTP)This repository holds client configuration only. The server is hosted at tokenusage.dev; its fields, caching and limits are documented at tokenusage.dev/developers.
Nerf Watch has a separate read-only MCP server for public benchmark scores and history. See Nerf Watch installation and tools. A lower score is a lower score on this suite, not proof that a provider changed a model. Data: tokenusage.dev linked to https://tokenusage.dev/nerfwatch.
| Tool | What it returns |
|---|---|
get_codex_reset_announcements | Codex usage-limit reset announcements by @thsottiaux on X, newest first (limit 1 to 50, default 10): each post's link, when it was posted, when tokenusage.dev recorded it and its resetType (automatic, banked or both; null for records older than reset types), plus when the monitor last checked X. |
get_codex_reset_calendar | The same announcements grouped by UTC calendar date, newest first, at most 50 in total; an optional month (YYYY-MM) selects one UTC month. A date without an entry does not mean no reset was announced. |
A banked reset grant saves a reset for eligible users to apply later and does not itself refill limits. A post is not proof that your own limit was reset: open its link for the exact wording, and check your Codex account for your personal reset times. Only @thsottiaux is watched.
Claude Code
claude mcp add --transport http tokenusage https://tokenusage.dev/mcp
or as a plugin:
claude plugin marketplace add stdcmms-lang/tokenusage-codex-mcp
claude plugin install tokenusage-codex@tokenusage
Codex
codex mcp add tokenusage --url https://tokenusage.dev/mcp
or as a plugin:
codex plugin marketplace add stdcmms-lang/tokenusage-codex-mcp
codex plugin add tokenusage-codex@tokenusage
Gemini CLI
gemini extensions install https://github.com/stdcmms-lang/tokenusage-codex-mcp
Cursor (.cursor/mcp.json) and other clients that take an mcpServers file:
{ "mcpServers": { "tokenusage": { "url": "https://tokenusage.dev/mcp" } } }
A client that supports only stdio servers can bridge with npx -y mcp-remote https://tokenusage.dev/mcp.
dev.tokenusage/codex (manifest: server.json)The data is free to reuse on one condition: where you show it to other people, in a site, app, bot message or dashboard, show Data: tokenusage.dev linked to https://tokenusage.dev/resets on the same screen or in the same message. Personal use needs no visible credit. Every response carries the link in its source field. See the terms.
Unofficial; not affiliated with OpenAI. Privacy: https://tokenusage.dev/privacy. Questions and corrections: https://tokenusage.dev/contact.
The configuration in this repository is MIT licensed. The hosted data is covered by the credit condition above.