Think Tool MCP Server
The Think Tool MCP Server enhances Claude's reasoning capabilities by providing a dedicated space for structured thinking during complex tasks.
Improves complex reasoning: Allows Claude to pause, reflect, and record internal thoughts as a scratchpad during response generation.
Structured problem-solving: Breaks down multi-step problems into clear, organized steps, improving consistency.
Policy compliance: Helps verify adherence to detailed policies and guidelines in various scenarios.
Tool integration: Works effectively with other MCP tools to analyze outputs and plan next steps.
Performance boost: Improves Claude's performance by up to 54% on complex tasks.
Important limitation: Does not perform external actions or retrieve new information.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Think Tool MCP ServerPlan how to refactor this legacy code before making changes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Think Tool MCP Server
Official implementation of Anthropic's "think" tool as an MCP server - Dramatically improve Claude's reasoning capabilities with structured thinking.
What is the Think Tool?
This MCP server implements the exact "think" tool that Anthropic introduced in their engineering blog post. The Think Tool provides Claude with a dedicated space for structured reasoning during complex problem-solving tasks, enabling more thoughtful, accurate, and reliable responses.
Related MCP server: MCP Think Tool Server
Proven Performance Benefits
Anthropic's research demonstrates remarkable improvements when using the "think" tool:
54% improvement in complex customer service tasks
Significantly better adherence to detailed policies and guidelines
Enhanced consistency across multiple trials of the same task
Improved performance on software engineering benchmarks
Minimal implementation overhead compared to other enhancement techniques
The "think" tool excels where other approaches fall short:
Better than extended thinking for cases requiring complex tool chains
More effective than baseline prompting for policy-heavy scenarios
Especially powerful when paired with optimized prompting
Quick Install
For Claude Desktop
npx -y @smithery/cli@latest install @PhillipRt/think-mcp-server --client claude --config "{}"For Cursor
npx -y @smithery/cli@latest install @PhillipRt/think-mcp-server --client cursor --config "{}"How It Works
The "think" tool implements the exact mechanism described in Anthropic's engineering blog. Unlike extended thinking (which happens before Claude starts responding), the "think" tool allows Claude to pause and reflect during its response generation.
Key mechanism: The tool doesn't perform any external actions or retrieve new information - it simply provides Claude with a dedicated scratchpad to work through reasoning step-by-step, which dramatically improves performance on complex tasks.
When Claude uses the "think" tool:
It pauses to organize thoughts before continuing a complex reasoning chain
It creates a structured approach to multi-step problems
It verifies policy compliance more thoroughly and consistently
It carefully analyzes tool outputs before deciding next steps
It maintains better context awareness across long interactions
When to Use the Think Tool
The "think" tool is especially valuable when:
Working with other MCP tools - Great for analyzing outputs from databases, filesystems, or APIs
Following complex policies - Perfect for customer service, legal, or compliance scenarios
Making sequential decisions - Ideal for workflows where later steps depend on earlier ones
Processing web search results - Helps Claude synthesize information from multiple sources
Solving coding challenges - Improves success rates on software engineering tasks
System Prompt for Optimal Results
Anthropic's research shows that combining the "think" tool with optimized prompting delivers the strongest performance improvements. For best results, add the following optimized system prompt to your Claude interaction:
For Claude Desktop (Custom Instructions)
Go to Settings > Custom Instructions
Add the following system prompt:
You have access to a "think" tool that provides a dedicated space for structured reasoning. Using this tool significantly improves your performance on complex tasks.
## When to use the think tool
Before taking any action or responding to the user after receiving tool results, use the think tool as a scratchpad to:
- List the specific rules that apply to the current request
- Check if all required information is collected
- Verify that the planned action complies with all policies
- Iterate over tool results for correctness
- Analyze complex information from web searches or other tools
- Plan multi-step approaches before executing them
## How to use the think tool effectively
When using the think tool:
1. Break down complex problems into clearly defined steps
2. Identify key facts, constraints, and requirements
3. Check for gaps in information and plan how to fill them
4. Evaluate multiple approaches before choosing one
5. Verify your reasoning for logical errors or biases
Remember that using the think tool has been shown to improve your performance by up to 54% on complex tasks, especially when working with multiple tools or following detailed policies.For Cursor (Global Rules)
To add the Think Tool as a Cursor Rule:
Open Cursor Settings
Navigate to General > Rules for AI
Add a new rule with the following content:
After any context change (viewing new files, running commands, or receiving tool outputs), use the "mcp_think" tool to organize your reasoning before responding.
Specifically, always use the think tool when:
- After examining file contents or project structure
- After running terminal commands or analyzing their outputs
- After receiving search results or API responses
- Before making code suggestions or explaining complex concepts
- When transitioning between different parts of a task
When using the think tool:
- List the specific rules or constraints that apply to the current task
- Check if all required information is collected
- Verify that your planned approach is correct
- Break down complex problems into clearly defined steps
- Analyze outputs from other tools thoroughly
- Plan multi-step approaches before executing them
The think tool has been proven to improve performance by up to 54% on complex tasks, especially when working with multiple tools or following detailed policies.Manual Installation
If you prefer to run the server locally:
Clone the repository:
git clone https://github.com/PhillipRt/think-mcp-server.git cd think-mcp-serverInstall dependencies:
npm installBuild and run:
npm run build npm startConfigure Claude Desktop manually:
Find or create the configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add your server configuration:
{ "mcpServers": { "think-tool": { "command": "node", "args": ["path/to/think-mcp-server/dist/server.js"] } } }
License
Available Tools
1 toolthinkA
Use the tool to think about something. It will not obtain new information or change the database, but just append the thought to the log. Use it when complex reasoning or some cache memory is needed.
| Name | Required | Description | Default |
|---|---|---|---|
| thought | Yes | A thought to think about. |
TDQS
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 will not obtain new information or change the database' clarifies it's a read-only, non-destructive operation, and 'just append the thought to the log' explains the action. This covers safety and basic behavior, though it could add details like log format or persistence.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized with two sentences that efficiently convey purpose and usage. It is front-loaded with the core action and avoids unnecessary details. Every sentence adds value, though minor improvements in clarity could enhance conciseness further.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one parameter, no annotations, no output schema), the description is reasonably complete. It covers purpose, usage, and behavioral traits adequately. However, it could be more specific about what 'think' involves or the log's nature, which would improve completeness for an agent's understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'thought' parameter documented as 'A thought to think about.' The description adds no additional parameter semantics beyond this, such as format or constraints. Given the high schema coverage, a baseline score of 3 is appropriate, as the schema already provides adequate parameter information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Use the tool to think about something' and 'append the thought to the log.' It specifies the verb ('think') and resource ('thought log'), though it doesn't distinguish from siblings since none exist. The purpose is clear but could be more specific about what 'think' entails operationally.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 the tool: 'Use it when complex reasoning or some cache memory is needed.' This gives clear context for its application. However, it lacks exclusions or alternatives, which is acceptable since no sibling tools are present to differentiate from.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
With only one tool, there is no possibility of ambiguity or overlap with other tools. The tool 'think' has a clearly distinct purpose of internal reasoning and logging, with no competing tools to confuse it with.
The single tool name 'think' follows a simple verb pattern, and with only one tool, there is no inconsistency to evaluate. The naming is straightforward and appropriate for its function.
A single tool is generally too few for most server purposes, as it limits functionality and can feel thin. For a 'Think Tool MCP Server', one tool might suffice for basic reasoning, but it lacks breadth and could be considered under-scoped for typical agent workflows.
The tool 'think' covers its specific purpose of reasoning and logging, but the server's domain is unclear from the single tool. There are no obvious gaps for the tool itself, but the overall surface is minimal, making it hard to assess completeness for any broader domain.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Agent personas for Claude. 16 tools, 13 personas, 3 workflows. Zero extra API cost. Free.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Reproducible benchmarks and reliability evidence for agent tools.
Stateless agentic tools over MCP: concept extraction, long-context, knowledge graph, planning.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that implements the 'think' tool, providing Claude with a dedicated space for structured thinking during complex problem-solving tasks to improve reasoning capabilities.131MIT
- AlicenseAqualityDmaintenanceImplements Anthropic's 'think' tool for Claude, providing a dedicated space for structured reasoning during complex problem-solving tasks that improves performance in reasoning chains and policy adherence.43,06038MIT
- FlicenseAqualityDmaintenanceAn MCP server implementation of Anthropic's Think Tool prompt engineering technique that enables Claude to break down complex problems and enhance its reasoning capabilities by providing a simple tool that echoes back thoughts.12
- AlicenseNot gradedqualityDmaintenanceProvides a 'think' tool that allows Claude and other LLMs to add dedicated thinking steps during complex tool use scenarios, creating space for structured reasoning and improving problem-solving capabilities.MIT
Appeared in Searches
- AI Prompting Techniques and Reasoning Methods
- A server for finding resources about deep thinking and critical thinking skills
- A server for finding content related to thinking or contemplation
- ADHD-related resources and information in Montgomery County Public Schools
- Methods to Enhance Deep Research Capabilities
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/PhillipRt/think-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server