Ollama

How it works

The /add-ollama-tool skill adds a stdio-based MCP server that connects the container agent to your local Ollama instance. The selected agent provider remains the orchestrator — it decides when to use a local model and what to send it. This is useful for offloading cheaper or faster tasks such as summarization, translation, or general knowledge queries.

The skill adds two tools to the agent:

• ollama_list_models — lists all models installed in your Ollama instance.
• ollama_generate — sends a prompt to a specified model and returns the response.

When a user sends a message like “use ollama to summarize this article,” the agent calls ollama_list_models to see what’s available, picks an appropriate model, and calls ollama_generate with the prompt. The local model’s response is incorporated into the agent’s reply.

Setup

The skill checks that Ollama is installed and running, then applies the code changes. It copies the MCP server into the container source tree and an env-forwarding helper into the host tree, registers the server in the agent-runner’s mcpServers, forwards OLLAMA_HOST / OLLAMA_ADMIN_TOOLS into the container, and rebuilds the image.

If you don’t have any Ollama models yet, the skill suggests starting with one of these:

• ollama pull gemma3:1b — small and fast (1 GB)
• ollama pull llama3.2 — good general purpose (2 GB)
• ollama pull qwen3-coder:30b — strong at code tasks (18 GB)

Network routing

The MCP server inside the container connects to Ollama on the host machine. It defaults to host.docker.internal:11434 and automatically falls back to localhost:11434 if that host is unreachable. If you’re running Ollama on a different machine or port, set OLLAMA_HOST in your .env file.

Monitoring

Monitor Ollama activity via the logs:

tail -f logs/nanoclaw.log | grep -i ollama

Look for [OLLAMA] >>> Generating and [OLLAMA] <<< Done entries.

Troubleshooting

Agent says “Ollama is not installed.” The agent is trying to run the ollama CLI inside the container instead of using the MCP tools. This means the MCP server wasn’t registered correctly. Re-run the skill or verify that container/agent-runner/src/index.ts has the ollama entry in its mcpServers config.

“Failed to connect to Ollama.” Verify Ollama is running on the host (ollama list). If using Docker, confirm the container can reach the host network. If using a custom host, check the OLLAMA_HOST value in .env.

Agent doesn’t use Ollama tools. The agent may not know the tools exist. Be explicit in your message: “use the ollama_generate tool with gemma3:1b to answer this.” Once the agent has used the tools once, it tends to remember them for future messages.

Tips

• The active agent decides when to use Ollama based on the task. You can nudge it by mentioning Ollama in your message.
• Smaller models respond faster but produce lower-quality output. For simple tasks like translation or factual lookups, a 1–2 GB model can be enough; keep harder reasoning with your primary provider.
• The Ollama MCP server runs as a stdio process inside the container — it starts with each agent session and stops when the session ends. There’s no persistent background process.