Skip to main content
Glama
harshpreet931

Long Reasoning MCP Server

sequentialthinking

Guide step-by-step reasoning through iterative revision, branching, and verification for deep problem-solving.

Instructions

A detailed tool for DEEP, EXTENSIVE, and dynamic problem-solving through extended thinking. This tool is designed for MAXIMUM DEPTH research and analysis with no artificial limits. Each thought can build on, question, or revise previous insights as understanding deepens.

IMPORTANT: For deep research tasks, you should:

  • Use 50+ thoughts minimum for complex problems, 100+ for deep research

  • Take time to explore multiple angles and perspectives

  • Question assumptions repeatedly throughout the process

  • Revise and refine understanding as you progress

  • Branch into alternative approaches when valuable

  • Generate multiple hypotheses and verify each thoroughly

  • Go as deep as needed - there is no maximum limit

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

  • Deep research requiring extensive exploration

  • Multi-hypothesis generation and verification

  • Comprehensive analysis across multiple dimensions

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

  • next_thought_needed: True if you need more thinking, even if at what seemed like the end

  • thought_number: Current number in sequence (can go beyond initial total if needed)

  • total_thoughts: Current estimate of thoughts needed (can be adjusted up/down)

  • is_revision: A boolean indicating if this thought revises previous thinking

  • revises_thought: If is_revision is true, which thought number is being reconsidered

  • branch_from_thought: If branching, which thought number is the branching point

  • branch_id: Identifier for the current branch (if any)

  • needs_more_thoughts: If reaching end but realizing more thoughts needed

You should:

  1. Start with an initial estimate of needed thoughts, but be ready to adjust UPWARD frequently

  2. Feel free to question or revise previous thoughts extensively

  3. Don't hesitate to add more thoughts if needed, even at the "end" - research has no artificial limits

  4. Express uncertainty when present and explore it deeply

  5. Mark thoughts that revise previous thinking or branch into new paths

  6. Ignore information that is irrelevant to the current step

  7. Generate MULTIPLE solution hypotheses when appropriate, not just one

  8. Verify each hypothesis thoroughly based on the Chain of Thought steps

  9. Repeat the hypothesis-verification cycle multiple times for robustness

  10. Explore edge cases, counterexamples, and alternative interpretations

  11. For deep research: aim for 100+ thoughts, exploring breadth AND depth

  12. Use branching extensively to explore alternative paths in parallel

  13. Perform multiple revision passes to refine understanding

  14. Only set next_thought_needed to false when truly done with COMPREHENSIVE analysis

  15. Provide a single, well-researched, thoroughly verified answer as the final output

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
thoughtYesYour current thinking step
nextThoughtNeededYesWhether another thought step is needed
thoughtNumberYesCurrent thought number (numeric value, e.g., 1, 2, 3)
totalThoughtsYesEstimated total thoughts needed (numeric value, e.g., 5, 10)
isRevisionNoWhether this revises previous thinking
revisesThoughtNoWhich thought is being reconsidered
branchFromThoughtNoBranching point thought number
branchIdNoBranch identifier
needsMoreThoughtsNoIf more thoughts are needed

Implementation Reference

  • index.ts:91-137 (handler)
    The main handler function `processThought` that executes the sequential thinking logic: validates input, stores thought in history, handles branching, formats output, and returns the result (or error).
    public processThought(input: unknown): { content: Array<{ type: string; text: string }>; isError?: boolean } {
      try {
        const validatedInput = this.validateThoughtData(input);
    
        if (validatedInput.thoughtNumber > validatedInput.totalThoughts) {
          validatedInput.totalThoughts = validatedInput.thoughtNumber;
        }
    
        this.thoughtHistory.push(validatedInput);
    
        if (validatedInput.branchFromThought && validatedInput.branchId) {
          if (!this.branches[validatedInput.branchId]) {
            this.branches[validatedInput.branchId] = [];
          }
          this.branches[validatedInput.branchId].push(validatedInput);
        }
    
        if (!this.disableThoughtLogging) {
          const formattedThought = this.formatThought(validatedInput);
          console.error(formattedThought);
        }
    
        return {
          content: [{
            type: "text",
            text: JSON.stringify({
              thoughtNumber: validatedInput.thoughtNumber,
              totalThoughts: validatedInput.totalThoughts,
              nextThoughtNeeded: validatedInput.nextThoughtNeeded,
              branches: Object.keys(this.branches),
              thoughtHistoryLength: this.thoughtHistory.length
            }, null, 2)
          }]
        };
      } catch (error) {
        return {
          content: [{
            type: "text",
            text: JSON.stringify({
              error: error instanceof Error ? error.message : String(error),
              status: 'failed'
            }, null, 2)
          }],
          isError: true
        };
      }
    }
  • The `ThoughtData` interface defining the input/output shape for the tool, including thought, thoughtNumber, totalThoughts, isRevision, revisesThought, branchFromThought, branchId, needsMoreThoughts, and nextThoughtNeeded.
    interface ThoughtData {
      thought: string;
      thoughtNumber: number;
      totalThoughts: number;
      isRevision?: boolean;
      revisesThought?: number;
      branchFromThought?: number;
      branchId?: string;
      needsMoreThoughts?: boolean;
      nextThoughtNeeded: boolean;
    }
  • index.ts:274-290 (registration)
    Tool registration via `ListToolsRequestSchema` (line 274-276) listing the SEQUENTIAL_THINKING_TOOL, and `CallToolRequestSchema` (line 278-290) dispatching calls with name 'sequentialthinking' to `processThought`.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [SEQUENTIAL_THINKING_TOOL],
    }));
    
    server.setRequestHandler(CallToolRequestSchema, async (request) => {
      if (request.params.name === "sequentialthinking") {
        return thinkingServer.processThought(request.params.arguments);
      }
    
      return {
        content: [{
          type: "text",
          text: `Unknown tool: ${request.params.name}`
        }],
        isError: true
      };
    });
  • Helper `validateThoughtData` that validates the input object has required fields (thought, thoughtNumber, totalThoughts, nextThoughtNeeded) with correct types, and returns a clean ThoughtData object.
    private validateThoughtData(input: unknown): ThoughtData {
      const data = input as Record<string, unknown>;
    
      if (!data.thought || typeof data.thought !== 'string') {
        throw new Error('Invalid thought: must be a string');
      }
      if (!data.thoughtNumber || typeof data.thoughtNumber !== 'number') {
        throw new Error('Invalid thoughtNumber: must be a number');
      }
      if (!data.totalThoughts || typeof data.totalThoughts !== 'number') {
        throw new Error('Invalid totalThoughts: must be a number');
      }
      if (typeof data.nextThoughtNeeded !== 'boolean') {
        throw new Error('Invalid nextThoughtNeeded: must be a boolean');
      }
    
      return {
        thought: data.thought,
        thoughtNumber: data.thoughtNumber,
        totalThoughts: data.totalThoughts,
        nextThoughtNeeded: data.nextThoughtNeeded,
        isRevision: data.isRevision as boolean | undefined,
        revisesThought: data.revisesThought as number | undefined,
        branchFromThought: data.branchFromThought as number | undefined,
        branchId: data.branchId as string | undefined,
        needsMoreThoughts: data.needsMoreThoughts as boolean | undefined,
      };
    }
  • Helper `formatThought` that creates the visual thought box with border, prefix (Revision/Branch/Thought), and thought number context, using chalk for coloring.
      private formatThought(thoughtData: ThoughtData): string {
        const { thoughtNumber, totalThoughts, thought, isRevision, revisesThought, branchFromThought, branchId } = thoughtData;
    
        let prefix = '';
        let context = '';
    
        if (isRevision) {
          prefix = chalk.yellow('🔄 Revision');
          context = ` (revising thought ${revisesThought})`;
        } else if (branchFromThought) {
          prefix = chalk.green('🌿 Branch');
          context = ` (from thought ${branchFromThought}, ID: ${branchId})`;
        } else {
          prefix = chalk.blue('💭 Thought');
          context = '';
        }
    
        const header = `${prefix} ${thoughtNumber}/${totalThoughts}${context}`;
        const border = '─'.repeat(Math.max(header.length, thought.length) + 4);
    
        return `
    ┌${border}┐
    │ ${header} │
    ├${border}┤
    │ ${thought.padEnd(border.length - 2)} │
    └${border}┘`;
      }
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses key behaviors like adjusting thoughts, revising, branching, and hypothesis verification. No annotations present, so description carries full burden and does well, though could mention side effects or limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very long with some redundancy (e.g., repeated emphasis on depth). Structured with sections, but could be more concise while retaining clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 9 parameters, no output schema, and no annotations, the description is thoroughly complete, covering all aspects needed for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and description adds extensive context for each parameter, explaining usage patterns, revision, branching, etc., beyond the schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly defines the tool as for deep, extensive, and dynamic problem-solving, specifying it for complex problems, research, and multi-step analysis. It is distinct and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a dedicated 'When to use this tool' section listing many appropriate scenarios, but does not explicitly mention when not to use or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/harshpreet931/longReasoningMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server