freemcplab / Directory / Playground / mcp-sequentialthinking-tools

● Community spences10 ⚡ Instant

mcp-sequentialthinking-tools

Name: mcp-sequentialthinking-tools MCP Server
Author: spences10

by spences10 · spences10/mcp-sequentialthinking-tools

Force your agent to think step-by-step AND suggest which other MCP tool to invoke at each step — a meta-planner for multi-tool workflows.

A fork of the canonical Sequential Thinking MCP that goes one step further: at every thought, it scores and recommends the best MCP tools from your installed set. Useful when Claude has 10+ MCPs loaded and keeps picking the wrong one.

▶ Watch demo 📦 Install 💡 Use Cases

Why use it

Key features

Step-by-step reasoning with confidence scores per step
Recommends which MCP tools to call at each step and why
Supports branching thoughts and revisions
Single tool, trivial to install and uninstall

Live Demo

What it looks like in practice

sequentialthinking-tools.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "sequentialthinking-tools": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-sequentialthinking-tools"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "sequentialthinking-tools": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-sequentialthinking-tools"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "sequentialthinking-tools": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-sequentialthinking-tools"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "sequentialthinking-tools": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-sequentialthinking-tools"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "sequentialthinking-tools",
      "command": "npx",
      "args": [
        "-y",
        "mcp-sequentialthinking-tools"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "sequentialthinking-tools": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-sequentialthinking-tools"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add sequentialthinking-tools -- npx -y mcp-sequentialthinking-tools

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use mcp-sequentialthinking-tools

How to plan a multi-MCP workflow with sequentialthinking-tools

👤 Power users with many MCPs installed ⏱ ~5 min beginner

When to use: You have Sentry + GitHub + Linear + Playwright + Notion all loaded and Claude keeps calling the wrong one or skipping steps.

Flow

Ask for a plan before execution

Before doing anything, use sequentialthinking_tools to plan: 'Triage the top Sentry issue, find the culprit commit on GitHub, file a Linear ticket.' Give 5 steps with tool recommendations.✓ Copied

→ Numbered plan with tool names + confidence scores
Execute one step at a time

Execute step 1. After done, show me the result and the next-step recommendation.✓ Copied

→ Clean handoff between tools without skipping checks

Outcome: Predictable tool usage, fewer wrong-tool detours, and an audit trail of reasoning.

Pitfalls

Model still picks a wrong tool despite the plan — Explicitly reject the bad choice in the next turn; the planner learns in-context

Break reasoning loops with sequentialthinking-tools

👤 Developers building agents that get stuck retrying ⏱ ~10 min intermediate

When to use: Your agent is looping on the same failing approach and not re-evaluating.

Flow

Force a revision

Use sequentialthinking_tools with is_revision=true to revisit step 3 of your current plan. What assumption was wrong?✓ Copied

→ A named assumption and an alternative tool or approach
Branch into a parallel plan

Create a branch from step 3 and propose a different tool path. Compare confidence to the original.✓ Copied

→ Two parallel paths scored

Outcome: Agent breaks out of the loop with a reasoned pivot.

Combine with: vibe-check

Combinations

Pair with other MCPs for X10 leverage

sequentialthinking-tools + vibe-check

Plan + sanity-check — sequentialthinking plans the steps, vibe-check challenges the plan before execution

Plan a refactor with sequentialthinking_tools, then call vibe_check to poke holes before I run it.✓ Copied

sequentialthinking-tools + shrimp-task-manager

Turn each planned step into a persistent task

Plan with sequentialthinking_tools, then hand each step to shrimp-task-manager as a tracked task.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
sequentialthinking_tools	thought: str, next_thought_needed: bool, thought_number: int, total_thoughts: int, is_revision?: bool, branch_from_thought?: int	Start of any multi-step or multi-MCP task where tool choice matters	0 — local reasoning wrapper

Cost & Limits

What this costs to run

API quota: None — runs locally
Tokens per call: 200–600 per thought
Monetary: Free
Tip: Cap total_thoughts at 5–7; longer chains rarely add value and spend tokens

Security

Permissions, secrets, blast radius

Credential storage: None required

Data egress: None — 100% local

Troubleshooting

Common errors and fixes

Tool recommendations are generic / unrelated to installed MCPs

The recommender works from names in the prompt — include a short list of your installed MCPs in the system prompt

Agent ignores the plan and jumps to action

Explicitly say 'do not call any other tool until you finish the sequential plan'

npx can't find the package

Try npm cache clean --force or pin a version: npx -y mcp-sequentialthinking-tools@latest

Verify: npx mcp-sequentialthinking-tools --help

Alternatives