# deepthonk

> deepthonk — linxule-deepthonk. Use this tool when you need to generate and rank candidate answers for complex problems, or when you require a flexible and budget-friendly solution for multi-round deep thinking tasks. DeepThonk provides a provider-neutral engine that accepts configurable budgets and model providers as inputs, and outputs ranked answers and inspection results. It is ideal for use cases that involve planning, running, and evaluating multiple rounds of candidate answer generation and ranking.

Canonical page: https://skillsregistry.net/skills/linxule-deepthonk  
JSON: https://api.skillsregistry.net/v1/skills/linxule-deepthonk

## Description

DeepThonk is an MCP server that provides a budget-friendly, provider-neutral deep-thinking engine based on the OpenDeepThink algorithm, enabling agents to plan, run, and inspect multi-round candidate answer generation and ranking tasks with configurable budgets and model providers.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/mo9vtxn11g)
- **Repository:** <https://github.com/linxule/deepthonk>

## 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": "linxule-deepthonk"
    }
  }
}
```

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