# Think

> Use this tool when you need to perform complex, multi-step reasoning on intricate problems, break down concepts, or explore competing hypotheses. It provides deep analytical thinking capabilities through AI modeling, enabling reliable and secure operation. Ideal for situations requiring extended reasoning chains without external information retrieval.

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

## Description

Think MCP provides deep analytical thinking capabilities through OpenAI's o3-mini model, enabling Claude to perform multi-step reasoning on complex problems. The implementation features robust error handling, rate limiting, and security measures to ensure reliable operation. It runs as a stdio transport server that integrates seamlessly with Claude Desktop, making it ideal for users who need to break down intricate concepts, explore competing hypotheses, or maintain multiple variables throughout extended reasoning chains without retrieving external information.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

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

## 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": "technavii-think"
    }
  }
}
```

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