# Dust

> Use this tool when you need to integrate cognitive neuroscience and problem-solving strategies into your AI workflows, especially for conversation management and dynamic agent interactions. It solves problems related to complex decision-making and information retrieval by bridging Claude with the Dust.tt AI agent platform. The Dust MCP Server takes in user inputs and outputs specialized agent interactions through a standardized MCP interface.

Canonical page: https://skillsregistry.net/skills/ma3u-dust  
JSON: https://api.skillsregistry.net/v1/skills/ma3u-dust

## Description

Dust MCP Server provides a bridge between Claude and the Dust.tt AI agent platform, specifically integrating a SystemsThinking agent that specializes in cognitive neuroscience and problem-solving strategies. Built by an AI research team, this implementation enables users to interact with specialized Dust agents through a standardized MCP interface, supporting features like conversation management, message retrieval, and dynamic agent interactions.

## Trust

- **Trust score (0–1):** 0.79
- **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/ma3u-dust)
- **Repository:** <https://github.com/ma3u/mcp-server-dust-py>

## 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": "ma3u-dust"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ma3u-dust` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ma3u-dust/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