MCP SERVER · OFFICIAL PROJECT

Sequential Thinking

Give the model a scratchpad it can revise and branch, for problems where the first plan is usually wrong.

by modelcontextprotocol ↗Reasoning Scaffolds & Agent Workflow Engines✓ Anthropic

The plugin Microsoft Agent Skills includes connection settings for this server.

LABSCO SUMMARY

One tool whose whole job is letting the model change its mind on the record.

You do not call it by hand — you connect it and the host calls it repeatedly while it works, which is what makes the reasoning visible as a numbered chain instead of one long answer. The parts that matter are revision and branching: a plan that turns out to rest on a bad assumption gets reopened at the step where the assumption entered, rather than restarted.

What it is

A single-tool server that structures step-by-step reasoning: each call carries one thought, its number, the estimated total, and whether another step is needed.

What you get

A problem broken into numbered steps, with the estimated total adjustable as the work goes on
Revision of an earlier step — isRevision and revisesThought mark which thought is being reconsidered
Alternative lines of reasoning, tracked with branchFromThought and branchId
An explicit continue-or-stop signal on every step, so the chain ends when the thinking is done rather than at a fixed length

Requirements

No account, no key, no network calls. Published on npm as @modelcontextprotocol/server-sequential-thinking and launched through npx; the package ships the mcp-server-sequential-thinking binary.

Setup effort

One command — npx -y @modelcontextprotocol/server-sequential-thinking

See installation options

USE CASES

01

Planning a migration where a step may turn out to be unacceptable

Work the plan out step by step and reopen the earlier step when a constraint — a downtime limit, say — rules it out.

sequentialthinking

02

Debugging something that only fails in one environment

Keep the hypotheses numbered so each eliminated one stays visible instead of being silently dropped.

sequentialthinking

03

Comparing architecture options that rest on different assumptions

Branch from the step where the assumptions diverge and carry both lines far enough to tell them apart.

sequentialthinking

04

Working a problem whose full scope is not clear at the start

Begin with an estimated number of steps and raise it as the shape of the problem emerges.

sequentialthinking

1 tool

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`sequentialthinking`

A detailed tool for dynamic and reflective problem-solving through thoughts. This tool helps analyze problems through a flexible thinking process that can adapt and evolve. Each thought can build on, question, or revise previous insights as understanding deepens.

When to use this tool:

Breaking down complex problems into steps
Planning and design with room for revision
Analysis that might need course correction
Problems where the full scope might not be clear initially
Problems that require a multi-step solution
Tasks that need to maintain context over multiple steps
Situations where irrelevant information needs to be filtered out

Key features:

You can adjust total_thoughts up or down as you progress
You can question or revise previous thoughts
You can add more thoughts even after reaching what seemed like the end
You can express uncertainty and explore alternative approaches
Not every thought needs to build linearly - you can branch or backtrack
Generates a solution hypothesis
Verifies the hypothesis based on the Chain of Thought steps
Repeats the process until satisfied
Provides a correct answer

Parameters explained:

thought: Your current thinking step, which can include:
Regular analytical steps
Revisions of previous thoughts
Questions about previous decisions
Realizations about needing more analysis
Changes in approach
Hypothesis generation
Hypothesis verification
nextThoughtNeeded: True if you need more thinking, even if at what seemed like the end
thoughtNumber: Current number in sequence (can go beyond initial total if needed)
totalThoughts: Current estimate of thoughts needed (can be adjusted up/down)
isRevision: A boolean indicating if this thought revises previous thinking
revisesThought: If is_revision is true, which thought number is being reconsidered
branchFromThought: If branching, which thought number is the branching point
branchId: Identifier for the current branch (if any)
needsMoreThoughts: If reaching end but realizing more thoughts needed

You should:

Start with an initial estimate of needed thoughts, but be ready to adjust
Feel free to question or revise previous thoughts
Don't hesitate to add more thoughts if needed, even at the "end"
Express uncertainty when present
Mark thoughts that revise previous thinking or branch into new paths
Ignore information that is irrelevant to the current step
Generate a solution hypothesis when appropriate
Verify the hypothesis based on the Chain of Thought steps
Repeat the process until satisfied with the solution
Provide a single, ideally correct answer as the final output
Only set nextThoughtNeeded to false when truly done and a satisfactory answer is reached

INSTALLATION

Connect your client

Add the block to your client, or run the command directly.

Server setup

Configuration file

JSON

{
  "mcpServers": {
    "server-sequential-thinking": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sequential-thinking"
      ]
    }
  }
}

npx

TERMINAL

npx -y @modelcontextprotocol/server-sequential-thinking