Add Ollama Tool (NanoClaw)

An installation skill that wires a local Ollama MCP server into NanoClaw so the container agent can run local models and optionally manage the model library.

Dev & CodingAdvanced★ 30,471⑂ 12,865AI score 7/10Last updated: Aug 9, 2026

What it does

Installs a stdio MCP server that exposes your local Ollama daemon as agent tools inside a NanoClaw project.
Core tools: ollama_list_models (installed models) and ollama_generate (prompt a chosen model).
Opt-in management tools with OLLAMA_ADMIN_TOOLS=true: pull, delete, show, and list-running models.
Walks the full wiring: copy source + tests, register ollama in the mcpServers map in container/agent-runner/src/index.ts, forward OLLAMA_HOST/OLLAMA_ADMIN_TOOLS in container-runner.ts, promote [OLLAMA] logs to info level, then build and run the wiring/registration tests.
Includes troubleshooting for connection failures, model 404s, pull timeouts, and missing admin tools.

Who it's for

Maintainers of a NanoClaw (nanocoai/nanoclaw) agent who can edit the project's source tree.
Teams who want to offload cheap work (summarizing, classification) to local models instead of paying per token.
Anyone experimenting with "Claude as orchestrator, local model as worker" setups.

Examples

After install, say "use ollama to tell me the capital of France" — the agent lists models, then calls ollama_generate.
With admin tools enabled, say "pull the gemma3:1b model" — the agent calls ollama_pull_model.
Ask "which ollama models are currently loaded in memory?" — the agent uses ollama_list_running to report memory usage and processor type.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/nanocoai/nanoclaw/HEAD/.claude/skills/add-ollama-tool/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .claude/skills/add-ollama-tool folder from the GitHub repo nanocoai/nanoclaw into my ~/.claude/skills/add-ollama-tool/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/nanocoai/nanoclaw.git && cp -r nanoclaw/.claude/skills/add-ollama-tool ~/.claude/skills/add-ollama-tool

⚠ This is a third-party skill. Check the source repository before installing.

Make sure you already have the NanoClaw project cloned locally — this skill assumes that exact repo layout.
Install Ollama on the host from https://ollama.com/download and start it (ollama serve or the desktop app).
Confirm the daemon responds: curl -s http://127.0.0.1:11434/api/tags. If no models exist, pull one: ollama pull gemma3:1b.
Install the skill: git clone https://github.com/nanocoai/nanoclaw.git && cp -r nanoclaw/.claude/skills/add-ollama-tool ~/.claude/skills/add-ollama-tool (if you already run NanoClaw, just use the in-repo .claude/skills/add-ollama-tool folder).
Open Claude Code at the project root and ask: "apply the add-ollama-tool skill to integrate Ollama".
After the agent copies files and edits index.ts / container-runner.ts, verify pnpm run build, the vitest/bun tests, and ./container/build.sh all pass.
Optionally add OLLAMA_ADMIN_TOOLS=true or OLLAMA_HOST=... to .env, restart the service (launchctl/systemctl), then verify with a message like "use ollama to ...".

View source on GitHub ↗License: MIT