Skip to main content
Glama

Codex Reset MCP server

Read-only facts about OpenAI Codex usage-limit resets, served by codex-reset.com over the Model Context Protocol.

This repository holds the client configuration and directory metadata for the hosted server. There is nothing to install or run: the server lives at the endpoint above, and its source is not published here.

Tools

All three tools are read-only (readOnlyHint: true) and read the same data as the site's public JSON API, so an agent and a browser never disagree.

Tool

Returns

Arguments

get_reset_forecast

Probability of a Codex usage-limit reset in the next 24 and 48 hours, confidence, the last confirmed reset and any active official signal. A forecast, not a promise.

locale

get_reset_timeline

Dated record of verified resets and related announcements, newest first, each with its source URL.

group (reset | boost | unlock | credits), from, to (YYYY-MM-DD), limit (1–50, default 10), locale

get_codex_status

Current Codex service state, to tell an outage apart from a usage limit.

locale

locale is en, zh, ja or es and changes only the human-readable copy.

Related MCP server: llm-quota-mcp

Example prompts

  • "Is Codex likely to reset its usage limits in the next 24 hours?"

  • "When was the last verified Codex usage-limit reset, and where was it announced?"

  • "List every Codex reset from August 2026 with its source link."

  • "I'm getting errors in Codex. Is that an outage or did I hit my usage limit?"

  • "Should I wait for a reset or keep working? Check the forecast and the service status."

Setup

Claude Code

claude mcp add --transport http codex-reset https://codex-reset.com/mcp

Or in .mcp.json:

{
  "mcpServers": {
    "codex-reset": { "type": "http", "url": "https://codex-reset.com/mcp" }
  }
}

This repository is also a Claude Code plugin (.claude-plugin/plugin.json + .mcp.json).

Codex CLI / IDE extension

~/.codex/config.toml:

[mcp_servers.codex-reset]
url = "https://codex-reset.com/mcp"

This repository is also a Codex plugin (.codex-plugin/plugin.json: the MCP server plus a codex-reset skill), listed in awesome-codex-plugins and the HOL plugin registry. The two config.toml lines above are all a plain Codex setup needs.

Cursor

.cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "codex-reset": { "url": "https://codex-reset.com/mcp" }
  }
}

VS Code (GitHub Copilot)

.vscode/mcp.json:

{
  "servers": {
    "codex-reset": { "type": "http", "url": "https://codex-reset.com/mcp" }
  }
}

Gemini CLI

gemini extensions install https://github.com/suvadadepolo-blip/codex-reset-mcp

Clients that only speak stdio

npx -y mcp-remote https://codex-reset.com/mcp

Check it by hand

curl -sS https://codex-reset.com/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Where it is listed

Terms

Reuse is free and keyless on one condition: credit. A site, app, bot message, dashboard, MCP tool or API that passes this data on names the source and links to it on the same surface: "Data: codex-reset.com", linked to https://codex-reset.com/. Personal use needs no visible credit. Full wording: codex-reset.com/developers and the terms of use.

Independent community project, not affiliated with OpenAI. "Codex" and "ChatGPT" are trademarks of OpenAI and are used only to describe what is being tracked.

License

The configuration files in this repository are MIT-licensed. The data served by the endpoint is covered by the terms above.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Live operational status for 2,400+ major software services — AWS, GitHub, Stripe, OpenAI, Cloudflare, and more — pulled from each provider's official status page and returned as a normalised up / degraded / down result for any service you ask about.
    5
    510 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables agents to check remaining Anthropic and OpenAI rate-limit quotas with reset times, plus Hermes Agent token usage, so bots can throttle or stop before hitting limits.
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI coding assistants and agent workflows to query live measured free-LLM performance and availability, including throughput, uptime, tool-calling success, and model diagnostics.
    4
    1
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Lets a coding agent inspect its own account's subscription limit windows, usage, and cost history, and decide whether to pause and sleep until a limit resets rather than failing mid-task. Supports multiple accounts and providers such as Claude Code and Codex.
    253 npm
    MIT