Does Sequentialthinking (reference) work with ChatGPT (Codex)?
Yes. Sequentialthinking (reference) passed every step of our test in ChatGPT (Codex) on Oct 14, 2026: it installed, connected, its tools were visible, and an agent used it to finish a real task.
Result
ResultPassed
Date testedOct 14, 2026
Plan tested onChatGPT Plus
App versioncodex-cli 0.162.0-alpha.17.2
Modelaccount default (ChatGPT Plus)
Steps
- install OK
- connected OK
- tools visible OK
- agent task: stepwise reasoning OKfor reasoning scratchpads that have no storage
From our own harness run, not the maker’s claims. How we test.
What happened in this run
Install config we used
[mcp_servers.ref-sequentialthinking]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-sequential-thinking"]Connection check
server answered tool calls during the taskTools check
verified via task step: agent saw and called the server's tools
Agent task: stepwise reasoning
- Tool calls, in order:
ref-sequentialthinking:sequentialthinking
Raw details from our harness log for this run. Secrets redacted.
Set it up in ChatGPT (Codex)
Copy-paste config for every app is on the Sequentialthinking (reference) page. Not connecting? ChatGPT (Codex) MCP troubleshooting.
Other apps we tested it in: Claude Code (passed) · Cursor (passed) · Claude Desktop (passed).