Skip to main content
Glama
cgize

MCP Think Tool Server

think

Facilitate structured reasoning and step-by-step analysis during complex problem-solving. Append thoughts to logs for policy verification, decision-making chains, and enhanced sequential reasoning processes without altering external states.

Instructions

Use this tool to think about something. It will not obtain new information or change anything, but just append the thought to the log. Use it when complex reasoning or cache memory is needed, especially during long chains of tool calls, policy adherence scenarios, or sequential decision making.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
thoughtYesA thought to think about. This can be structured reasoning, step-by-step analysis, policy verification, or any other mental process that helps with problem-solving.

Implementation Reference

  • The handler function for the "think" tool. It logs the input thought with a timestamp to the thoughtsLog array and returns a confirmation message in the MCP format.
    async ({ thought }) => {
      // Log the thought with a timestamp
      const timestamp = new Date().toISOString();
      this.thoughtsLog.push({
        timestamp,
        thought
      });
      
      console.error(`[${timestamp}] Thought recorded: ${thought.substring(0, 50)}${thought.length > 50 ? '...' : ''}`);
      
      // Return a confirmation
      return {
        content: [{ 
          type: "text", 
          text: `Thought recorded: ${thought.length > 50 ? thought.substring(0, 50) + '...' : thought}` 
        }]
      };
    }
  • The input schema for the "think" tool, defining a single string parameter 'thought' using Zod validation.
    { thought: z.string().describe("A thought to think about. This can be structured reasoning, step-by-step analysis, policy verification, or any other mental process that helps with problem-solving.") },
  • src/index.ts:31-52 (registration)
    The registration of the "think" tool using the McpServer.tool() method, including name, description, schema, and handler function.
      "think",
      "Use this tool to think about something. It will not obtain new information or change anything, but just append the thought to the log. Use it when complex reasoning or cache memory is needed, especially during long chains of tool calls, policy adherence scenarios, or sequential decision making.",
      { thought: z.string().describe("A thought to think about. This can be structured reasoning, step-by-step analysis, policy verification, or any other mental process that helps with problem-solving.") },
      async ({ thought }) => {
        // Log the thought with a timestamp
        const timestamp = new Date().toISOString();
        this.thoughtsLog.push({
          timestamp,
          thought
        });
        
        console.error(`[${timestamp}] Thought recorded: ${thought.substring(0, 50)}${thought.length > 50 ? '...' : ''}`);
        
        // Return a confirmation
        return {
          content: [{ 
            type: "text", 
            text: `Thought recorded: ${thought.length > 50 ? thought.substring(0, 50) + '...' : thought}` 
          }]
        };
      }
    );
Behavior4/5

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 effectively describes key traits: it's a non-destructive operation ('will not... change anything'), doesn't fetch external data ('not obtain new information'), and has a logging effect ('append the thought to the log'). However, it lacks details on rate limits, authentication needs, or error handling.

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

Conciseness5/5

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

The description is concise and front-loaded, with two sentences that efficiently convey purpose and usage guidelines. Every sentence adds value without redundancy, making it easy for an AI agent to parse quickly.

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

Completeness4/5

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

Given the tool's low complexity (1 parameter, no output schema, no annotations), the description is mostly complete. It covers purpose, usage, and behavioral traits adequately. However, it doesn't explain the log's format or how thoughts are stored/retrieved, which might be relevant for sibling tools like 'get_thoughts'.

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

Parameters3/5

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

The schema description coverage is 100%, so the parameter 'thought' is well-documented in the schema. The description adds minimal value beyond this, mentioning 'structured reasoning, step-by-step analysis' which aligns with but doesn't significantly expand on the schema's description. Baseline 3 is appropriate given high schema coverage.

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: 'to think about something' and 'append the thought to the log.' It specifies the verb ('think') and resource ('thought log'), but doesn't explicitly differentiate from sibling tools like 'clear_thoughts' or 'get_thoughts' beyond mentioning it 'appends' thoughts.

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 provides explicit guidance on when to use this tool: 'when complex reasoning or cache memory is needed, especially during long chains of tool calls, policy adherence scenarios, or sequential decision making.' It also clarifies when not to use it: 'It will not obtain new information or change anything,' though it doesn't name specific 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

Related Tools

  • @abhinav-mangla/think-tool-mcp
  • @flight505/mcp-think-tank
  • @PhillipRt/think-mcp-server
  • @piotrpalek/mcp-thinking-tool
  • @hanzoai/mcp
  • @marcopesani/think-mcp-server

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/cgize/claude-mcp-think-tool'

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