# Think

> Use this tool when you need to facilitate complex reasoning and step-by-step analysis for AI assistants, providing a dedicated thinking space that acknowledges thoughts with random encouragements. It solves problems requiring memory retention and introspective processing without external actions, making it ideal for scenarios like decision-making and problem-solving. The Think tool accepts thoughts as input and provides encouragements as output, integrating seamlessly with MCP-compatible clients.

Canonical page: https://skillsregistry.net/skills/marcopesani-think  
JSON: https://api.skillsregistry.net/v1/skills/marcopesani-think

## Description

A minimal MCP server that implements Anthropic's 'think' tool research, allowing AI assistants to use a dedicated thinking space for complex reasoning. The server provides a simple interface where thoughts are acknowledged with random encouragements, making it ideal for scenarios requiring step-by-step analysis or memory retention without performing external actions. Built with TypeScript and the MCP SDK, it's containerized for easy deployment and designed to integrate with MCP-compatible clients like Cursor.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/marcopesani-think)
- **Repository:** <https://github.com/marcopesani/think-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "marcopesani-think"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/marcopesani-think` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/marcopesani-think/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt