add-atomic-chat-tool

Expose local Atomic Chat models as MCP tools for the NanoClaw container agent.

Updated May 7, 2026
One-click install
npx skills add https://github.com/Bartunek/nanoclaw --skill add-atomic-chat-tool-bartunek
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-atomic-chat-tool
Source: https://github.com/Bartunek/nanoclaw/tree/main/.claude/skills/add-atomic-chat-tool
Command: npx skills add https://github.com/Bartunek/nanoclaw --skill add-atomic-chat-tool-bartunek

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Expose local Atomic Chat models as tools for the NanoClaw container agent.

Core Features & Use Cases

  • Stdio-based MCP server that exposes local Atomic Chat models as OpenAI-compatible tools at http://127.0.0.1:1337/v1, enabling the container agent to offload tasks to host models.
  • Tools exposed:
    • atomic_chat_list_models: list available models
    • atomic_chat_generate: generate a response from a selected model
  • Seamless integration: registers the MCP server in the container and forwards host environment variables to ensure the host API is reachable from the container.

Quick Start

Start NanoClaw with Atomic Chat installed on the host, ensure the local API is reachable, then install this skill and rebuild the container to enable the MCP tool.

Frequently Asked Questions about add-atomic-chat-tool

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I expose local Atomic Chat models as agent tools in a container?

You expose local Atomic Chat models as agent tools by running a stdio-based MCP server that connects the NanoClaw container agent to the local API at http://127.0.0.1:1337/v1.

What tools are available when integrating local Atomic Chat models with an agent?

The integration provides two tools: atomic_chat_list_models for listing available local models, and atomic_chat_generate for generating a response from a selected model.

Do I need to configure environment variables for the container agent to reach the local API?

Yes, the MCP server automatically forwards host environment variables during container registration to ensure the local Atomic Chat API remains reachable from within the container.

How does an MCP server connect a container agent to a local OpenAI-compatible API?

A Bun-based MCP server implements stdio communication, registers within the container's agent-runner wiring, and bridges the container agent to the host's local OpenAI-compatible API endpoints.

Can I use NanoClaw to offload agent tasks to host models?

Yes, NanoClaw container agents can offload tasks to host models by utilizing the exposed Atomic Chat tools, provided Atomic Chat is installed and the local API is reachable.

What steps are needed to activate the local Atomic Chat MCP server in NanoClaw?

Start NanoClaw with Atomic Chat installed, ensure the local API is reachable, install the skill, and rebuild the container to register the MCP server and enable the tools.