# llama-diffusion-mcp

> Use this tool when you need to facilitate communication between large language models (LLMs) and diffusion-based LLMs, enabling bidirectional chat and session management. It solves problems of compatibility and session persistence between different AI models, allowing for seamless interaction and configuration. This tool is ideal for use cases requiring flexible and persistent dialogue between LLMs, with inputs including chat prompts and configuration settings, and outputs including responsive dialogue and session state.

Canonical page: https://skillsregistry.net/skills/hkbu-kennycheng-llama-diffusion-mcp  
JSON: https://api.skillsregistry.net/v1/skills/hkbu-kennycheng-llama-diffusion-mcp

## Description

Enables LLMs like Claude to bidirectionally chat with diffusion-based LLMs (e.g., DiffusionGemma, LLaDA) via a persistent llama-diffusion-cli process, with support for restarting sessions and full configuration.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/aqkszm17he)
- **Repository:** <https://github.com/hkbu-kennycheng/llama-diffusion-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": "hkbu-kennycheng-llama-diffusion-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hkbu-kennycheng-llama-diffusion-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hkbu-kennycheng-llama-diffusion-mcp/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