skills.rest
thmtz
thmtzCOMMUNITY
Explore all skills by this author →
GitHub

add-atomic-chat-tool

Deploy a stdio-based MCP server to expose Atomic Chat model tools to container agents.

5|Updated Apr 2, 2026
Search Tags:#container#mcp-server#local-models#openai-api#agent-runner#atomic-chat
One-click install
npx skills add https://github.com/thmtz/nanoclaw-fleet --skill add-atomic-chat-tool-thmtz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-atomic-chat-tool
Source: https://github.com/thmtz/nanoclaw-fleet/tree/main/.claude/skills/add-atomic-chat-tool
Command: npx skills add https://github.com/thmtz/nanoclaw-fleet --skill add-atomic-chat-tool-thmtz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Containerized NanoClaw agents currently cannot access local AI models; this skill enables an MCP server to bridge to the host's Atomic Chat models.

Core Features & Use Cases

  • Local model access: Connect container agents to Atomic Chat-hosted models via an OpenAI-compatible API.
  • MCP server integration: Wire a stdio-based MCP server into the agent-runner, exposing tools like atomic_chat_list_models and atomic_chat_generate.
  • Use Case: Develop and test on a local machine without sending data to external services.

Quick Start

Use this skill to enable the agent to discover and call a local model via Atomic Chat.

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 connect a container agent to local models using an MCP server?▼

To connect a container agent to local models, you deploy a stdio-based MCP server wired into the agent-runner, exposing tools like atomic_chat_generate. This bridges the container to the host's Atomic Chat models via an OpenAI-compatible API.

Can I use an OpenAI-compatible API to access local models from a containerized agent?▼

Yes, you can access local models from a containerized agent by configuring an MCP server. It bridges the container to the host's Atomic Chat models using an OpenAI-compatible API, allowing local development without sending data to external services.

What tools are exposed when integrating Atomic Chat with an agent runner?▼

Integrating Atomic Chat with an agent runner exposes two specific MCP tools: atomic_chat_list_models and atomic_chat_generate. These tools enable the container agent to discover available local models and generate responses through the host's API.

How do I configure host settings and API keys for a local model MCP server?▼

You configure host settings and optional API keys by modifying the agent runtime code during MCP server integration. These settings establish the connection between the stdio-based MCP server and the host's Atomic Chat local models.

Why use a local Atomic Chat MCP server instead of external API services for agent development?▼

Use a local Atomic Chat MCP server to develop and test agents on a local machine without sending data to external services. This approach provides secure access to local models via an OpenAI-compatible API directly from the container.

Related Skills

Explore More Software Engineering Skills→
AIsa-teamAIsa-team
23

cn-llm

Route chat, coding, and reasoning requests to Chinese LLMs via an OpenAI-compatible AIsa API.

Official
Basic
BartunekBartunek

add-atomic-chat-tool

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

Community
Advanced
rnbenrnben

native-mcp

Connect Hermes Agent to MCP servers and register discovered tools.

Community
Advanced
chiptoe-svgchiptoe-svg

add-atomic-chat-tool

Connect NanoClaw agents to Atomic Chat's OpenAI-compatible API for local model access.

Community
Intermediate