This skill adds a stdio-based MCP server that exposes models running in the local Atomic Chat desktop app as tools for the container agent. Claude remains the orchestrator but can offload work to local models served by Atomic Chat on http://127.0.0.1:1337/v1 (OpenAI-compatible).
Tools exposed:
\natomic_chat_list_models — list models currently available in Atomic Chat (GET /v1/models)atomic_chat_generate — send a prompt to a specified model and return the response (POST /v1/chat/completions)Model management (download, delete) is done through the Atomic Chat desktop UI — the app is a fork of Jan and manages its own model library.
\nThe skill ships the MCP server source (and its test) in this folder and copies them into the agent-runner tree at install time, then registers the server in index.ts and forwards host env vars in container-runner.ts. Registering the server is enough to expose its tools — the agent's allow-pattern (mcp__atomic_chat__*) is derived from the registered server name.
Check if container/agent-runner/src/atomic-chat-mcp-stdio.ts exists. If it does, skip to Phase 3 (Configure).
Verify Atomic Chat is installed and its local API server is running. On the host:
\ncurl -s http://127.0.0.1:1337/v1/models | head\nIf the request fails:
\natomic-chat.dmg).1337.This skill reaches into both the container (Bun) tree and the host (Node) tree, so its\nfiles go into both, alongside the integration points they cover.
\nS=.claude/skills/add-atomic-chat-tool\n# Container (Bun) tree — the MCP server and the registration wiring test\ncp $S/atomic-chat-mcp-stdio.ts container/agent-runner/src/atomic-chat-mcp-stdio.ts\ncp $S/atomic-chat-registration.test.ts container/agent-runner/src/atomic-chat-registration.test.ts\n# Host (Node) tree — the env-forwarding helper and the wiring test\ncp $S/atomic-chat-env.ts src/atomic-chat-env.ts\ncp $S/atomic-chat-wiring.test.ts src/atomic-chat-wiring.test.ts\nEdit container/agent-runner/src/index.ts. Find the mcpServers object that currently looks like this:
const mcpServers: Record<string, { command: string; args: string[]; env: Record<string, string> }> = {\n nanoclaw: {\n command: 'bun',\n args: ['run', mcpServerPath],\n env: {},\n },\n };\nAdd an atomic_chat entry alongside nanoclaw:
const mcpServers: Record<string, { command: string; args: string[]; env: Record<string, string> }> = {\n nanoclaw: {\n command: 'bun',\n args: ['run', mcpServerPath],\n env: {},\n },\n atomic_chat: {\n command: 'bun',\n args: ['run', path.join(__dirname, 'atomic-chat-mcp-stdio.ts')],\n env: {\n ...(process.env.ATOMIC_CHAT_HOST ? { ATOMIC_CHAT_HOST: process.env.ATOMIC_CHAT_HOST } : {}),\n ...(process.env.ATOMIC_CHAT_API_KEY ? { ATOMIC_CHAT_API_KEY: process.env.ATOMIC_CHAT_API_KEY } : {}),\n },\n },\n };\natomic-chat-registration.test.ts asserts this entry is present and points at the server module — the tool only appears to the agent if it is registered here.
The env-forwarding logic lives in the copied src/atomic-chat-env.ts (atomicChatEnv()), so the reach-in into composeSessionSpec is a single spread.
Import it in src/container-runner.ts (alongside the other local imports):
import { atomicChatEnv } from './atomic-chat-env.js';\nThen, in composeSessionSpec, find the contributedEnv literal and spread the helper at the end. The contributed lane — not the composed env literal — because ATOMIC_CHAT_API_KEY is credential-NAMED and the composed lane's key-name check would refuse the spawn; the contributed lane exempts the name and still refuses credential-shaped values:
const contributedEnv: Record<string, string> = {\n ...(contribution.env ?? {}),\n ...(gateway.env ?? {}),\n ...atomicChatEnv(),\n };\natomic-chat-wiring.test.ts asserts this ...atomicChatEnv() spread exists inside composeSessionSpec.
[ATOMIC] log lines at info level\n\nShared block. This rewrites the driver's container-stderr logger, which other local-model tools (e.g.
\nadd-ollama-toolfor[OLLAMA]) also edit to surface their own prefix. Touch only the[ATOMIC]branch and leave the rest of the block intact, so the edits coexist and removal restores it cleanly.
Container stderr now lands in the Docker driver: in src/drivers/docker-driver.ts, inside DockerHandle.start(), find the stderr handler:
proc.onStderr((line) => {\n log.debug(line, { container: this.name });\n this.#stderrTail.push(line);\n if (this.#stderrTail.length > 10) this.#stderrTail.shift();\n });\nReplace the log.debug line with a prefix branch (leave the stderr-tail lines intact — they feed the non-zero-exit warning):
proc.onStderr((line) => {\n if (line.includes('[ATOMIC]')) {\n log.info(line, { container: this.name });\n } else {\n log.debug(line, { container: this.name });\n }\n this.#stderrTail.push(line);\n if (this.#stderrTail.length > 10) this.#stderrTail.shift();\n });\n.env.exampleAppend to .env.example:
# Atomic Chat MCP tool (.claude/skills/add-atomic-chat-tool)\n# Override the host where Atomic Chat exposes its OpenAI-compatible API.\n# Default: http://host.docker.internal:1337 (with fallback to localhost)\n# ATOMIC_CHAT_HOST=http://host.docker.internal:1337\n\n# Optional API key. Leave unset for a local Atomic Chat install — it does not require auth.\n# ATOMIC_CHAT_API_KEY=\npnpm run build\npnpm exec tsc -p container/agent-runner/tsconfig.json --noEmit\n# Host tree: composeSessionSpec wiring\npnpm exec vitest run src/atomic-chat-wiring.test.ts\n# Container tree: index.ts registration\n(cd container/agent-runner && bun test src/atomic-chat-registration.test.ts)\n./container/build.sh\nAll must be clean before proceeding. The wiring and registration tests confirm the two\nintegration points — the composeSessionSpec spread and the index.ts registration — are\nactually in place; a failure means one drifted. (The MCP server's own request/response\nbehavior against Atomic Chat is the author's build-time concern, not part of these tests —\nverify it manually in Phase 4.)
By default, the MCP server connects to http://host.docker.internal:1337 (Docker Desktop) with a fallback to localhost. To use a custom host, add to .env:
ATOMIC_CHAT_HOST=http://your-atomic-chat-host:1337\nAtomic Chat does not require authentication when running locally — leave this unset. Only set it if you've put Atomic Chat behind a reverse proxy that enforces auth:
\nATOMIC_CHAT_API_KEY=sk-...\nRun from your NanoClaw project root:
\nsource setup/lib/install-slug.sh\nlaunchctl kickstart -k gui/$(id -u)/$(launchd_label) # macOS\n# Linux: systemctl --user restart $(systemd_unit)\nTell the user:
\n\n\nSend a message like: \"use atomic chat to tell me the capital of France\"
\nThe agent should use
\natomic_chat_list_modelsto find available models, thenatomic_chat_generateto get a response.
tail -f logs/nanoclaw.log | grep -i atomic\nLook for:
\n[ATOMIC] Listing models... — list request started[ATOMIC] Found N models — models discovered[ATOMIC] >>> Generating with <model> — generation started[ATOMIC] <<< Done: <model> | Xs | N tokens | M chars — generation completedThe agent is looking for a CLI that doesn't exist instead of using the MCP tools. This means:
\ncontainer/agent-runner/src/atomic-chat-mcp-stdio.ts existscontainer/agent-runner/src/index.ts has the atomic_chat entry in mcpServers (the allow-pattern is derived from this, so registration is the only thing to check)./container/build.shcurl http://127.0.0.1:1337/v1/modelsdocker run --rm curlimages/curl curl -s http://host.docker.internal:1337/v1/modelsATOMIC_CHAT_HOST in .envmodel not found / 404 on generateThe model ID passed to atomic_chat_generate must exactly match one of the IDs returned by atomic_chat_list_models. Ask the agent to list models first, then pick one from that list.
Atomic Chat lazy-loads models into memory on first use. The initial call may take longer while the model warms up. Subsequent calls against the same model are fast.
\nThe agent may not know about the tools. Try being explicit: \"use the atomic_chat_generate tool with llama3.2-3b-instruct to answer: ...\"
\nAtomic Chat respects each model's native context length. If you hit limits, pass max_tokens explicitly when calling atomic_chat_generate, or switch to a model with a larger context window in the Atomic Chat UI.