Codex vs Claude Code MCP server

Which MCP servers are Codex vs Claude Code's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-27

← Back to Codex vs Claude Code

Whose server it is

Registry namedev.tokenusage/codexverified in the MCP registry

The registry name sits under tokenusage.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-27

Stateanswerschecked 2026-10-27
Tools2
Server calls itselfdev.tokenusage/codex
Server version1.1.0
Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 101 ms.

Should an agent connect itNot proven either way yet

Whether its tools do the product's job has not been judged yet.
Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-27

INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
Answeredmeasuring1 of the 7 daily checks it takes to print a share
Median first answer112 ms
Space in an agent's context≈ 610 tokensthe definitions of all its tools (2), which an agent carries on every turn
Tool definitionsA · 100 of 100
Typed results2 of 2 toolsdeclared outputSchema: results come typed, read once

Every tool passes all six checks.

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers2 tools · read 2026-10-27

get_codex_reset_announcements
Codex usage-limit reset announcements recorded by tokenusage.dev's Reset Alerts from @thsottiaux's public posts on X, newest first (at most 50): each post's link, when it was posted, when this site recorded it and resetType, plus when the…
get_codex_reset_calendar
Codex usage-limit reset announcements recorded by tokenusage.dev's Reset Alerts from @thsottiaux's public posts on X, grouped by UTC calendar date, newest dates first, with posts within each date newest first (at most 50 announcements in…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "codex": {
      "type": "http",
      "url": "https://tokenusage.dev/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http tokenusage https://tokenusage.dev/mcp

Add to Cursor Add to VS Code

claude.ai, ChatGPT and other clients: add https://tokenusage.dev/mcp as a custom connector in the settings.

Other servers listed as Codex vs Claude Code's

dev.tokenusage/nerfwatchanswers, 2 toolsverified in the MCP registry

OpenAPI spec

3 paths, read 2026-10-27. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.