---
name: Ollama Integration
slug: ollama-integration
category: AI Engineering
description: Ollama Integration adds an MCP server that exposes local Ollama models as tools for the container agent. Use it when you want Claude to offload summarization, translation, or other queries to a local model.
github: "https://github.com/sbusso/claudeclaw/tree/main/skills/add-ollama-tool"
language: TypeScript
stars: 193
forks: 60
install: "npx degit https://github.com/sbusso/claudeclaw/tree/main/skills/add-ollama-tool ~/.claude/skills/add-ollama-tool"
installs_to: ~/.claude/skills/add-ollama-tool
source_path: skills/add-ollama-tool/SKILL.md
collection_size: 25
category_size: 3278
collection_url: "https://dirskills.com/collections/sbusso/claudeclaw"
added: 2026-09-06T05:19:00.123Z
last_synced: 2026-09-06T05:19:00.123Z
canonical_url: "https://dirskills.com/skills/ollama-integration"
---

# Ollama Integration

Ollama Integration adds an MCP server that exposes local Ollama models as tools for the container agent. Use it when you want Claude to offload summarization, translation, or other queries to a local model.

**Install:**

```bash
npx degit https://github.com/sbusso/claudeclaw/tree/main/skills/add-ollama-tool ~/.claude/skills/add-ollama-tool
```

## README

# Add Ollama Integration

This skill adds a stdio-based MCP server that exposes local Ollama models as tools for the container agent. Claude remains the orchestrator but can offload work to local models.

Tools added:
- `ollama_list_models` — lists installed Ollama models
- `ollama_generate` — sends a prompt to a specified model and returns the response

## Phase 1: Pre-flight

### Check if already applied

Check if `agent/runner/src/ollama-mcp-stdio.ts` exists. If it does, skip to Phase 3 (Configure).

### Check prerequisites

Verify Ollama is installed and running on the host:

```bash
ollama list
```

If Ollama is not installed, direct the user to https://ollama.com/download.

If no models are installed, suggest pulling one:

> You need at least one model. I recommend:
>
> ```bash
> ollama pull gemma3:1b    # Small, fast (1GB)
> ollama pull llama3.2     # Good general purpose (2GB)
> ollama pull qwen3-coder:30b  # Best for code tasks (18GB)
> ```

## Phase 2: Apply Code Changes

### Ensure upstream remote

```bash
git remote -v
```

If `upstream` is missing, add it:

```bash
git remote add upstream https://github.com/sbusso/claudeclaw.git
```

### Merge the skill branch

```bash
git fetch upstream skill/ollama-tool
git merge upstream/skill/ollama-tool
```

This merges in:
- `agent/runner/src/ollama-mcp-stdio.ts` (Ollama MCP server)
- `scripts/ollama-watch.sh` (macOS notification watcher)
- Ollama MCP config in `agent/runner/src/index.ts` (allowedTools + mcpServers)
- `[OLLAMA]` log surfacing in `src/orchestrator/container-runner.ts`
- `OLLAMA_HOST` in `.env.example`

If the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides.

### Copy to per-group agent-runner

Existing groups have a cached copy of the agent-runner source. Copy the new files:

```bash
for dir in data/sessions/*/agent-runner-src; do
  cp agent/runner/src/ollama-mcp-stdio.ts "$dir/"
  cp agent/runner/src/index.ts "$dir/"
done
```

### Validate code changes

```bash
npm run build
./src/runtimes/docker/build.sh
```

Build must be clean before proceeding.

## Phase 3: Configure

### Set Ollama host (optional)

By default, the MCP server connects to `http://host.docker.internal:11434` (Docker Desktop) with a fallback to `localhost`. To use a custom Ollama host, add to `.env`:

```bash
OLLAMA_HOST=http://your-ollama-host:11434
```

> **Service name:** Derived from the directory name: `com.claudeclaw.<dirname>` (macOS) / `claudeclaw-<dirname>` (Linux). For example, if cwd is `my-assistant`, the service is `com.claudeclaw.my-assistant`. Determine the correct service name before running service commands below.

### Restart the service

```bash
launchctl kickstart -k gui/$(id -u)/com.claudeclaw  # macOS
# Linux: systemctl --user restart claudeclaw
```

## Phase 4: Verify

### Test via WhatsApp

Tell the user:

> Send a message like: "use ollama to tell me the capital of France"
>
> The agent should use `ollama_list_models` to find available models, then `ollama_generate` to get a response.

### Monitor activity (optional)

Run the watcher script for macOS notifications when Ollama is used:

```bash
./scripts/ollama-watch.sh
```

### Check logs if needed

```bash
tail -f logs/claudeclaw.log | grep -i ollama
```

Look for:
- `Agent output: ... Ollama ...` — agent used Ollama successfully
- `[OLLAMA] >>> Generating` — generation started (if log surfacing works)
- `[OLLAMA] <<< Done` — generation completed

## Troubleshooting

### Agent says "Ollama is not installed"

The agent is trying to run `ollama` CLI inside the container instead of using the MCP tools. This means:
1. The MCP server wasn't registered — check `agent/runner/src/index.ts` has the `ollama` entry in `mcpServers`
2. The per-group source wasn't updated — re-copy files (see Phase 2)
3. The container wasn't rebuilt — run `./src/runtimes/docker/build.sh`

### "Failed to connect to Ollama"

1. Verify Ollama is running: `ollama list`
2. Check Docker can reach the host: `docker run --rm curlimages/curl curl -s http://host.docker.internal:11434/api/tags`
3. If using a custom host, check `OLLAMA_HOST` in `.env`

### Agent doesn't use Ollama tools

The agent may not know about the tools. Try being explicit: "use the ollama_generate tool with gemma3:1b to answer: ..."