Skip to main content
Glama
cmarin

Sequential Thinking MCP Server

by cmarin

sequentialthinking

Solve complex problems through dynamic, step-by-step analysis with flexible revision and branching capabilities. Break down challenges into manageable thoughts while adjusting your approach as understanding evolves.

Instructions

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

  • 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

  2. Feel free to question or revise previous thoughts

  3. Don't hesitate to add more thoughts if needed, even at the "end"

  4. Express uncertainty when present

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

  6. Ignore information that is irrelevant to the current step

  7. Generate a solution hypothesis when appropriate

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

  9. Repeat the process until satisfied with the solution

  10. Provide a single, ideally correct answer as the final output

  11. Only set next_thought_needed to false when truly done and a satisfactory answer is reached

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
thoughtYesYour current thinking step
nextThoughtNeededYesWhether another thought step is needed
thoughtNumberYesCurrent thought number
totalThoughtsYesEstimated total thoughts needed
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)
    Core execution logic for the sequentialthinking tool: validates and processes thought data, manages history and branches, logs formatted output, returns JSON status.
    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
        };
      }
    }
  • Input schema defining parameters for the tool call including thought, numbering, branching, and revision flags.
    inputSchema: {
      type: "object",
      properties: {
        thought: {
          type: "string",
          description: "Your current thinking step"
        },
        nextThoughtNeeded: {
          type: "boolean",
          description: "Whether another thought step is needed"
        },
        thoughtNumber: {
          type: "integer",
          description: "Current thought number",
          minimum: 1
        },
        totalThoughts: {
          type: "integer",
          description: "Estimated total thoughts needed",
          minimum: 1
        },
        isRevision: {
          type: "boolean",
          description: "Whether this revises previous thinking"
        },
        revisesThought: {
          type: "integer",
          description: "Which thought is being reconsidered",
          minimum: 1
        },
        branchFromThought: {
          type: "integer",
          description: "Branching point thought number",
          minimum: 1
        },
        branchId: {
          type: "string",
          description: "Branch identifier"
        },
        needsMoreThoughts: {
          type: "boolean",
          description: "If more thoughts are needed"
        }
      },
      required: ["thought", "nextThoughtNeeded", "thoughtNumber", "totalThoughts"]
    }
  • index.ts:258-260 (registration)
    Tool registration in the ListToolsRequestHandler, exposing sequentialthinking in the tools list.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [SEQUENTIAL_THINKING_TOOL],
    }));
  • index.ts:262-274 (registration)
    CallToolRequestHandler dispatch that routes calls to 'sequentialthinking' to the processThought handler.
    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 function to validate and type-check the incoming thought data against ThoughtData interface.
    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,
      };
    }
Behavior5/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains key features (e.g., 'You can adjust total_thoughts up or down as you progress', 'You can question or revise previous thoughts') and provides 11 detailed behavioral instructions (e.g., 'Start with an initial estimate...', 'Feel free to question or revise...'), covering how the tool adapts, handles revisions, branching, and final output generation. This goes well beyond basic functionality.

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 well-structured with clear sections (purpose, when to use, key features, parameters explained, instructions), but it is overly verbose with repetitive points (e.g., multiple mentions of revising thoughts or adding more thoughts). Some sentences could be condensed without losing clarity, as not every sentence earns its place efficiently.

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 the complexity of a 9-parameter tool with no annotations and no output schema, the description is highly complete. It covers purpose, usage guidelines, behavioral traits, parameter semantics, and step-by-step instructions, providing all necessary context for an agent to understand and use the tool effectively without relying on structured fields.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds significant value with a 'Parameters explained' section that elaborates on each parameter's purpose and usage context (e.g., for 'thought', it lists examples like 'Regular analytical steps', 'Revisions of previous thoughts'; for 'is_revision', it clarifies the relationship with 'revises_thought'). This provides deeper semantic meaning beyond the schema's basic descriptions.

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

Purpose4/5

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

The description clearly states the tool's purpose as 'dynamic and reflective problem-solving through thoughts' and 'analyze problems through a flexible thinking process', which is specific about the verb (problem-solving/analysis) and resource (thoughts/thinking process). However, since there are no sibling tools mentioned, it cannot differentiate from alternatives, preventing a perfect score.

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

Usage Guidelines5/5

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

The description explicitly provides a 'When to use this tool' section with 7 specific scenarios (e.g., 'Breaking down complex problems into steps', 'Planning and design with room for revision'), giving clear guidance on appropriate contexts without any misleading information. This is comprehensive and directly addresses when to use the tool.

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/cmarin/sequentialthinking-mcp'

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