Ollama MCP Server with

@angrysky56

About Ollama MCP Server with

Use fast-agent to use MCP tools with local LLM, API or Claude Desktop. WIP

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ollama-mcp-server": {
      "command": "uv",
      "args": [
        "venv",
        "--python",
        "3.12",
        "--seed"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Ollama MCP Server?

Ollama MCP Server is a comprehensive Model Context Protocol (MCP) server for integrating Ollama with advanced features including script management, multi-agent workflows, and process leak prevention. It enables Claude Desktop to interact with locally installed Ollama models through MCP tools.

How to use Ollama MCP Server?

Install with Python 3.8+ and the uv package manager, then configure Claude Desktop using the provided example config file. After updating paths and restarting Claude Desktop, invoke tools like list_ollama_models or run_ollama_prompt directly from the Claude interface.

Key features of Ollama MCP Server

Async job management for long-running tasks
Script templates with variable substitution
Multi-agent workflows: chain, parallel, router, evaluator
Process leak prevention and resource cleanup
Comprehensive job tracking and monitoring
Support for any locally installed Ollama model

Use cases of Ollama MCP Server

Execute prompts with any Ollama model synchronously or asynchronously
Create and run reusable prompt templates with variables
Coordinate multi-agent workflows like chain or parallel
Compare multiple models side by side
Batch process multiple prompts efficiently

FAQ from Ollama MCP Server

What are the prerequisites?

Python 3.8+ with the uv package manager, Ollama installed and running, and Claude Desktop for MCP integration.

How do I install the Ollama MCP Server?

Create a virtual environment, add mcp[cli] and python-dotenv, then configure Claude Desktop with the provided example config file and update paths.

What does the server do for process management?

It includes signal handling, background task tracking, resource cleanup, and automatic process termination to prevent process leaks.

How do I troubleshoot a stuck job?

Use the cancel_job tool to stop problematic tasks.

How do I connect to Ollama?

Ollama must be running locally; use ollama serve if needed. List available models with list_ollama_models.

Frequently asked questions

What are the prerequisites?

Python 3.8+ with the `uv` package manager, Ollama installed and running, and Claude Desktop for MCP integration.

How do I install the Ollama MCP Server?

Create a virtual environment, add `mcp[cli]` and `python-dotenv`, then configure Claude Desktop with the provided example config file and update paths.

What does the server do for process management?

It includes signal handling, background task tracking, resource cleanup, and automatic process termination to prevent process leaks.

How do I troubleshoot a stuck job?

Use the `cancel_job` tool to stop problematic tasks.

How do I connect to Ollama?

Ollama must be running locally; use `ollama serve` if needed. List available models with `list_ollama_models`.

Comments

Basic information

More AI & Agents MCP servers

Competitor Tracker & Co.

Competitor Tracker & Co. watches your competitors' websites and tells you what changed. Every week it crawls their pricing, product, messaging and corporate pages, detects the changes that matter, and files a tagged, ran

fhirHydrant

faulkj

Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

早

早起鸟儿喊真人验真

shenshaoyin

早起鸟儿喊真人验真 is a remote MCP server available at http://121.40.18.232.

q-ring

I4cTime

Quantum-inspired keyring for AI coding agents. Secure secrets with superposition, entanglement, tunneling, and teleportation — CLI + 44 MCP tools.

Magic Hour

Magic Hour MCP lets AI agents create and edit images, videos, and audio using Magic Hour’s hosted generation tools.