mcp-ollama
About
MCP server wrapping local Ollama models for Claude Code delegation
Details
- Author
- true-alter
- Downloads
- 164
- Categories
- AI
Jump to
- Nine tools for generation, summarisation, code, diffs, and more
- Runs entirely over stdio – no network call‑outs by the server
- Override model per tool call or via OLLAMA_MODEL environment variable
- Ships no model weights, no telemetry, no analytics
- Stateless between calls; every request stays on the host running Ollama
- Supports Docker deployment with automatic host‑network routing
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
mcp-ollamaCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via npm install -g @truealter/mcp-ollama or run with npx @truealter/mcp-ollama. You need a running Ollama instance with at least one model pulled (default hermes3:8b). Configure the server in your MCP client (e.g., Claude Code) using stdio transport and optionally set OLLAMA_HOST and OLLAMA_MODEL environment variables. Tools are exposed automatically via MCP introspection.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp-ollama": {
"ollama": {
"command": "node",
"args": [
"/absolute/path/to/mcp-ollama/dist/index.js"
],
"env": {
"OLLAMA_HOST": "http://localhost:11434",
"OLLAMA_MODEL": "hermes3:8b"
}
}
}
}
}McpServers
{
"ollama": {
"command": "node",
"args": [
"/absolute/path/to/mcp-ollama/dist/index.js"
],
"env": {
"OLLAMA_HOST": "http://localhost:11434",
"OLLAMA_MODEL": "hermes3:8b"
}
}
}mcp-ollama
MCP server wrapping local Ollama models for offload from API-priced orchestrators.
Exposes nine tools that pass work to a local model (text generation, summarisation, code tasks, mechanical transforms, commit/PR/changelog drafting). The orchestrator decides what to route locally; this server does the routing.
- Transport: stdio
- Runtime: Node 18+
- Default model: hermes3:8b (override via OLLAMA_MODEL)
- Ollama host: http://localhost:11434 (override via OLLAMA_HOST)
- Ships no model weights, no cloud call-outs, no telemetry. Every request stays on the host where Ollama is running.
- License: Apache-2.0
Why
Orchestrators priced by the token (Claude Code, Cursor, the Anthropic API, Cline, Aider) pay for every classification, every docstring, every commit message. Most of that work doesn't need a frontier model. Routed to Ollama on the same machine, the same work is free and faster. mcp-ollama is the routing surface.
The orchestrating model decides what to route where. This server is plumbing - it does not try to be clever about task classification. Pick the right tool, pass the text, get a result back.
Install
Install (npm)
npm install -g @truealter/mcp-ollama
Or invoke directly without installing:
npx @truealter/mcp-ollama
You also need a running Ollama instance with at least one model pulled:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
