Happy slice of mcp pizzaMCP.pizza

mcp-sequentialthinking-tools

MCP.Pizza Chef: spences10

Think of it as a numbered scratchpad the assistant writes into while it works. Each step is recorded, and steps can be revised, branched, or cleared, with the whole history readable afterwards. Despite what older descriptions suggest, it does not find or pick tools for you: it only checks that any tool names the assistant proposes appear on a list you supply. It is free, needs no account, and installs by pasting a few lines into your app's settings.

Coding
Other

Use This MCP server To

Watch how my assistant broke a big task into steps Ask it to revise step three and try again Compare two different plans for the same problem Keep a running plan across a long working session Clear the plan history and start fresh

README

mcp-sequentialthinking-tools

built with vite+ tested with vitest

A lightweight MCP server for recording sequential reasoning steps. It is a scratchpad with history, branching, revision metadata, and optional validation for model-authored tool plans.

It does not discover your other MCP tools and it does not choose tools for the model. If you pass available_tools and recommended_tools, the server validates that the recommended names exist and stores the step.

Why use it?

Use this when a task benefits from explicit, inspectable reasoning:

  • breaking a messy problem into steps;
  • revising or branching a plan;
  • keeping a small reasoning history by session;
  • validating tool-plan names against a supplied tool list;
  • clearing or inspecting reasoning history during a long agent run.

Do not use it for trivial requests. It adds overhead.

Tools

sequentialthinking_tools

Records one thought.

Required parameters:

  • thought — current reasoning step
  • thought_number — current step number
  • total_thoughts — current estimate; automatically raised if lower than thought_number
  • next_thought_needed — whether another thought is needed

Optional parameters:

  • session_id — history bucket; defaults to default
  • is_revision, revises_thought
  • branch_from_thought, branch_id
  • needs_more_thoughts
  • available_tools — array of tool names or { name, description } objects
  • recommended_tools — model-authored recommendations to validate/store
  • remaining_steps — short list of upcoming steps

Example:

mcp-sequentialthinking-tools FAQ

Does it choose the best tools for me?
No. Despite the name, it records steps and only checks proposed tool names against a list you provide.
Do I need an account or key?
No. It runs on your own machine and costs nothing.
Which apps does it work in?
Claude Desktop and other apps that support MCP servers.
How hard is the setup?
Easy. Paste a few lines into your app's config file and restart it.
Can I use this to plan a complicated task?
Yes — it is built for messy problems where you want every step written down and open to revision.
Is it worth using for quick questions?
No. The author says it adds overhead and should be skipped for simple requests.
Is the text I put in it kept safe?
Step text is scanned and suspicious instructions are stripped out, but never put passwords or secrets in it.