How to add Sequential Thinking to Windsurf
Structured step-by-step reasoning tool for breaking problems into revisable thought sequences. Paste the config into ~/.codeium/windsurf/mcp_config.json and restart Windsurf.
Last updated June 15, 2026 · 62k★ · stdio · no auth · official
Windsurf config for Sequential Thinking
npx -y @modelcontextprotocol/server-sequential-thinking{
"mcpServers": {
"sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}Setup steps
- 1Open Windsurf → Cascade → the hammer/MCP icon → Configure (or edit ~/.codeium/windsurf/mcp_config.json).
- 2Paste the Sequential Thinking config below.
- 3Fill in placeholder secrets, then save.
- 4Click Refresh in the MCP panel.
- 5Sequential Thinking's tools become available to Cascade.
Before you start
- Node.js with npx (for the npm package), OR
- Docker installed and running (to use the mcp/sequentialthinking image)
- No API key or network access required
What Sequential Thinking can do in Windsurf
sequentialthinkingRecord one reasoning step with thought, thoughtNumber, totalThoughts, and nextThoughtNeeded; supports optional isRevision/revisesThought, branchFromThought/branchId, and needsMoreThoughts for revision and branching
Security
Runs entirely locally with no network access or stored data, so the attack surface is minimal. The only risk is the usual one of executing an npm package, so pin to the official scope.
Sequential Thinking + Windsurf FAQ
Where is the Windsurf config file?
Windsurf reads MCP servers from ~/.codeium/windsurf/mcp_config.json. Paste the Sequential Thinking config there under the "mcpServers" key and restart the client.
Is Sequential Thinking safe to use with Windsurf?
Runs entirely locally with no network access or stored data, so the attack surface is minimal. The only risk is the usual one of executing an npm package, so pin to the official scope.
Does it need an API key or internet access?
No. It is a self-contained local reasoning tool — no credentials, no network calls, no external services.
What tool does it actually expose?
A single tool, `sequentialthinking`, which records one reasoning step per call with parameters like thoughtNumber, totalThoughts, and nextThoughtNeeded, plus optional revision and branching fields.
How do I stop it from printing thoughts to the console?
Set the environment variable DISABLE_THOUGHT_LOGGING=true in the server's env block to disable the formatted thought logging.