Does Sequentialthinking (reference) work with Claude Code?

Yes. Sequentialthinking (reference) passed every step of our test in Claude Code on Oct 13, 2026: it installed, connected, its tools were visible, and an agent used it to finish a real task.

Result

ResultPassed
Date testedOct 13, 2026
Plan tested onClaude Pro
App version2.1.296 (Claude Code)
Modelhaiku

Steps

  1. install OK
  2. connected OK
  3. tools visible OK
  4. 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

claude mcp add -s local ref-sequentialthinking -- npx -y @modelcontextprotocol/server-sequential-thinking

Connection check

ref-sequentialthinking: npx -y @modelcontextprotocol/server-sequential-thinking - ✔ Connected

Tools check

verified via task step: agent saw and called the server's tools

Agent task: stepwise reasoning

  • Tool calls, in order: mcp__ref-sequentialthinking__sequentialthinking

Raw details from our harness log for this run. Secrets redacted.

Set it up in Claude Code

Copy-paste config for every app is on the Sequentialthinking (reference) page. Not connecting? Claude Code MCP troubleshooting.

Other apps we tested it in: Cursor (passed) · Claude Desktop (passed) · ChatGPT (Codex) (passed).

All MCP servers tested in Claude Code

Sponsors