# Deepseek R1 Reasoner

> Use this tool when you need to enable autonomous planning and decision-making in AI agents, or perform task planning and context-based reasoning without relying on remote models. The Deepseek R1 Reasoner provides a local reasoning extension for running Deepseek r1 models, accepting input from local sources and outputting planned tasks and strategies. It is ideal for applications requiring data privacy, low latency, and advanced problem-solving capabilities.

Canonical page: https://skillsregistry.net/skills/michaelneale-deepseek-r1-reasoner  
JSON: https://api.skillsregistry.net/v1/skills/michaelneale-deepseek-r1-reasoner

## Description

This MCP server, developed by an unspecified author, provides a reasoning extension for locally running models using Deepseek r1. Built with TypeScript and leveraging the Model Context Protocol SDK, it offers a tool for task planning and context-based reasoning. The implementation focuses on enabling AI agents to perform reasoning tasks without relying on remote models, using Ollama to run Deepseek r1 locally. It's particularly useful for applications requiring autonomous planning and decision-making capabilities, enabling use cases such as task decomposition, strategy formulation, and context-aware problem-solving while maintaining data privacy and reducing latency.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/michaelneale-deepseek-r1-reasoner)
- **Repository:** <https://github.com/michaelneale/deepseek-r1-mcp>

## 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": "michaelneale-deepseek-r1-reasoner"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/michaelneale-deepseek-r1-reasoner` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/michaelneale-deepseek-r1-reasoner/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