codex-reset-mcpSAFE
Hosted read-only MCP server for OpenAI Codex usage-limit resets: 24/48h forecast, verified reset record, service status. No API key.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/servers/suvadadepolo/codex-reset)
Read-only facts about OpenAI Codex usage-limit resets, served by codex-reset.com over the Model Context Protocol.
- Endpoint:
https://codex-reset.com/mcp - Transport: Streamable HTTP, JSON-RPC 2.0, protocol
2025-06-18. POST only; a GET answers 405. - Auth: none. No API key, no sign-up, no session.
- Cost: free, with credit (see Terms).
- Docs: codex-reset.com/developers · terminal walkthrough on dev.to · server card · llms.txt
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.
locale is en, zh, ja or es and changes only the human-readable copy.
Example prompts
- "Is Codex likely to re
dbab9fc20b5bOBSERVED · 2026-10-11Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
streamable-http
.codexignore
Gates applied: no_behavioural_pass.
dbab9fc20b5bfull audit observations/trust-audit/mcp-server/suvadadepolo-blip__codex-reset-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | dbab9fc20b5b | SAFE | B | 89 | first audit |
Questions
What is the codex-reset-mcp MCP server?
Hosted read-only MCP server for OpenAI Codex usage-limit resets: 24/48h forecast, verified reset record, service status. No API key.
Is codex-reset-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does codex-reset-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does codex-reset-mcp run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (dbab9fc20b5b), read on 2026-10-11. The repository is watched and re-audited when it changes.