A simple yet powerful Python client for interacting with Model Context Protocol (MCP) servers using Ollama, allowing local LLMs to use tools.

---

MCP Client for Ollama (ollmcp)

Table of Contents

• Overview
• Features
• Requirements
• Quick Start
• Usage
  • Command-line Arguments
  • Usage Examples
• Interactive Commands
  • Tool and Server Selection
  • Model Selection
  • Advanced Model Configuration
  • Server Reloading for Development
  • Human-in-the-Loop (HIL) Tool Execution
• Configuration Management
• Server Configuration Format
• Compatible Models
• Where Can I Find More MCP Servers?
• License
• Acknowledgments

Overview

This project provides a robust Python-based client that connects to one or more Model Context Protocol (MCP) servers and uses Ollama to process queries with tool use capabilities. The client establishes connections to MCP servers, sends queries to Ollama models, and handles the tool calls the model makes.

This implementation was adapted from the Model Context Protocol quickstart guide and customized to work with Ollama, providing a user-friendly interface for interacting with LLMs that support function calling.

Features

• 🌐 Multi-Server Support: Connect to multiple MCP servers simultaneously
• 🚀 Multiple Transport Types: Supports STDIO, SSE, and Streamable HTTP server connections
• 🎨 Rich Terminal Interface: Interactive console UI
• 🖥️ Streaming Responses: View model outputs in real-time as they're generated
• 🛠️ Tool Management: Enable/disable specific tools or entire servers during chat sessions
• 🧑‍💻 Human-in-the-Loop (HIL): Review and approve tool executions before they run for enhanced control and safety
• 🎛️ Advanced Model Configuration: Fine-tune 10+ model parameters including temperature, sampling, repetition control, and more
• 💬 System Prompt Customization: Define and edit the system prompt to control model behavior and persona
• 🎨 Enhanced Tool Display: Beautiful, structured visualization of tool executions with JSON syntax highlighting
• 🧠 Context Management: Control conversation memory with configurable retention settings
• 🤔 Thinking Mode: Advanced reasoning capabilities with visible thought processes for supported models (deepseek-r1, qwen3)
• 🗣️ Cross-Language Support: Seamlessly work with both Python and JavaScript MCP servers
• 🔍 Auto-Discovery: Automatically find and use Claude's existing MCP server configurations
• 🔁 Dynamic Model Switching: Switch between any installed Ollama model without restarting
• 💾 Configuration Persistence: Save and load tool preferences between sessions
• 🔄 Server Reloading: Hot-reload MCP servers during development without restarting the client
• 📊 Usage Analytics: Track token consumption and conversation history metrics
• 🔌 Plug-and-Play: Works immediately with standard MCP-compliant tool servers
• 🔔 Update Notifications: Automatically detects when a new version is available

Requirements

• Python 3.10+ (Installation guide)
• Ollama running locally (Installation guide)
• UV package manager (Installation guide)

Quick Start

Option 1: Install with pip and run

pip install ollmcp
ollmcp

Option 2: One-step install and run

uvx ollmcp

Option 3: Install from source and run using virtual environment

git clone https://github.com/jonigl/mcp-client-for-ollama.git
cd mcp-client-for-ollama
uv venv && source .venv/bin/activate
uv pip install .
uv run -m mcp_client_for_ollama

Usage

Run with default settings:

ollmcp

If you don't provide any options, the client will use auto-discovery mode to find MCP servers from Claude's configuration.

Command-line Arguments

Server Options:

• --mcp-server: Path to one or more MCP server scripts (.py or .js). Can be specified multiple times.
• --servers-json: Path to a JSON file with server configurations.
• --auto-discovery: Auto-discover servers from Claude's default config file (default behavior if no other options provided).

[!TIP] Claude's configuration file is typically located at: ~/Library/Application Support/Claude/claude_desktop_config.json

Model Options:

• --model MODEL: Ollama model to use. Default: qwen2.5:7b
• --host HOST: Ollama host URL. Default: http://localhost:11434

Usage Examples

Connect to a single server:

ollmcp --mcp-server /path/to/weather.py --model llama3.2:3b

Connect to multiple servers:

ollmcp --mcp-server /path/to/weather.py --mcp-server /path/to/filesystem.js --model qwen2.5:latest

Use a JSON configuration file:

ollmcp --servers-json /path/to/servers.json --model llama3.2:1b

Use a custom Ollama host:

ollmcp --host http://localhost:22545 --servers-json /path/to/servers.json --model qwen3:latest

Interactive Commands

During chat, use these commands:

Tool and Server Selection

The tool and server selection interface allows you to enable or disable specific tools:

• Enter numbers separated by commas (e.g. 1,3,5) to toggle specific tools
• Enter ranges of numbers (e.g. 5-8) to toggle multiple consecutive tools
• Enter S + number (e.g. S1) to toggle all tools in a specific server
• a or all - Enable all tools
• n or none - Disable all tools
• d or desc - Show/hide tool descriptions
• s or save - Save changes and return to chat
• q or quit - Cancel changes and return to chat

Model Selection

The model selection interface shows all available models in your Ollama installation:

• Enter the number of the model you want to use
• s or save - Save the model selection and return to chat
• q or quit - Cancel the model selection and return to chat

Advanced Model Configuration

The model-config (mc) command opens the advanced model settings interface, allowing you to fine-tune how the model generates responses:

System Prompt

• System Prompt: Set the model's role and behavior to guide responses.

Key Parameters

• Keep Tokens: Prevent important tokens from being dropped
• Max Tokens: Limit response length (0 = auto)
• Seed: Make outputs reproducible (set to -1 for random)
• Temperature: Control randomness (0 = deterministic, higher = creative)
• Top K / Top P / Min P / Typical P: Sampling controls for diversity
• Repeat Last N / Repeat Penalty: Reduce repetition
• Presence/Frequency Penalty: Encourage new topics, reduce repeats
• Stop Sequences: Custom stopping points (up to 8)

Commands

• Enter parameter numbers 1-14 to edit settings
• Enter sp to edit the system prompt
• Use u1, u2, etc. to unset parameters, or uall to reset all
• h/help: Show parameter details and tips
• undo: Revert changes
• s/save: Apply changes
• q/quit: Cancel

Example Configurations

• Factual: temperature: 0.0-0.3, top_p: 0.1-0.5, seed: 42
• Creative: temperature: 1.0+, top_p: 0.95, presence_penalty: 0.2
• Reduce Repeats: repeat_penalty: 1.1-1.3, presence_penalty: 0.2, frequency_penalty: 0.3
• Balanced: temperature: 0.7, top_p: 0.9, typical_p: 0.7
• Reproducible: seed: 42, temperature: 0.0

[!TIP] All parameters default to unset, letting Ollama use its own optimized values. Use help in the config menu for details and recommendations. Changes are saved with your configuration.

Server Reloading for Development

The reload-servers command (rs) is particularly useful during MCP server development. It allows you to reload all connected servers without restarting the entire client application.

Key Benefits:

• 🔄 Hot Reload: Instantly apply changes to your MCP server code
• 🛠️ Development Workflow: Perfect for iterative development and testing
• 📝 Configuration Updates: Automatically picks up changes in server JSON configs or Claude configs
• 🎯 State Preservation: Maintains your tool enabled/disabled preferences across reloads
• ⚡️ Time Saving: No need to restart the client and reconfigure everything

When to Use:

• After modifying your MCP server implementation
• When you've updated server configurations in JSON files
• After changing Claude's MCP configuration
• During debugging to ensure you're testing the latest server version

Simply type reload-servers or rs in the chat interface, and the client will:

1. Disconnect from all current MCP servers
2. Reconnect using the same parameters (server paths, config files, auto-discovery)
3. Restore your previous tool enabled/disabled settings
4. Display the updated server and tool status

This feature dramatically improves the development experience when building and testing MCP servers.

Human-in-the-Loop (HIL) Tool Execution

The Human-in-the-Loop feature provides an additional safety layer by allowing you to review and approve tool executions before they run. This is particularly useful for:

• 🛡️ Safety: Review potentially destructive operations before execution
• 🔍 Learning: Understand what tools the model wants to use and why
• 🎯 Control: Selective execution of only the tools you approve
• 🚫 Prevention: Stop unwanted tool calls from executing

HIL Confirmation Display

When HIL is enabled, you'll see a confirmation prompt before each tool execution:

Example:

🧑‍💻 Human-in-the-Loop Confirmation
Tool to execute: weather.get_weather
Arguments:
  • city: Miami

Options:
  y/yes - Execute the tool call
  n/no - Skip this tool call
  disable - Disable HIL confirmations permanently

What would you like to do? (y):

Human-in-the-Loop (HIL) Configuration

• Default State: HIL confirmations are enabled by default for safety
• Toggle Command: Use human-in-loop or hil to toggle on/off
• Persistent Settings: HIL preference is saved with your configuration
• Quick Disable: Choose "disable" during any confirmation to turn off permanently
• Re-enable: Use the hil command anytime to turn confirmations back on

Benefits:

• Enhanced Safety: Prevent accidental or unwanted tool executions
• Awareness: Understand what actions the model is attempting to perform
• Selective Control: Choose which operations to allow on a case-by-case basis
• Peace of Mind: Full visibility and control over automated actions

Configuration Management

[!TIP] It will automatically load the default configuration from ~/.config/ollmcp/config.json if it exists.

The client supports saving and loading tool configurations between sessions:

• When using save-config, you can provide a name for the configuration or use the default
• Configurations are stored in ~/.config/ollmcp/ directory
• The default configuration is saved as ~/.config/ollmcp/config.json
• Named configurations are saved as ~/.config/ollmcp/{name}.json

The configuration saves:

• Current model selection
• Advanced model parameters (system prompt, temperature, sampling settings, etc.)
• Enabled/disabled status of all tools
• Context retention settings
• Thinking mode settings
• Tool execution display preferences
• Human-in-the-Loop confirmation settings

Server Configuration Format

The JSON configuration file supports STDIO, SSE, and Streamable HTTP server types:

{
  "mcpServers": {
    "stdio-server": {
      "command": "command-to-run",
      "args": ["arg1", "arg2", "..."],
      "env": {
        "ENV_VAR1": "value1",
        "ENV_VAR2": "value2"
      },
      "disabled": false
    },
    "sse-server": {
      "type": "sse",
      "url": "http://localhost:8000/sse",
      "headers": {
        "Authorization": "Bearer your-token-here"
      },
      "disabled": false
    },
    "http-server": {
      "type": "streamable_http",
      "url": "http://localhost:8000/mcp",
      "headers": {
        "X-API-Key": "your-api-key-here"
      },
      "disabled": false
    }
  }
}

[!NOTE] If you specify a URL without a type, the client will default to using Streamable HTTP transport.

Compatible Models

The following Ollama models work well with tool use:

• qwen2.5
• qwen3
• llama3.1
• llama3.2
• mistral

For a complete list of Ollama models with tool use capabilities, visit the official Ollama models page.

How Tool Calls Work

1. The client sends your query to Ollama with a list of available tools
2. If Ollama decides to use a tool, the client:
   • Displays the tool execution with formatted arguments and syntax highlighting
   • NEW: Shows a Human-in-the-Loop confirmation prompt (if enabled) allowing you to review and approve the tool call
   • Extracts the tool name and arguments from the model response
   • Calls the appropriate MCP server with these arguments (only if approved or HIL is disabled)
   • Shows the tool response in a structured, easy-to-read format
   • Sends the tool result back to Ollama for final processing
   • Displays the model's final response incorporating the tool results

Where Can I Find More MCP Servers?

You can explore a collection of MCP servers in the official MCP Servers repository.

This repository contains reference implementations for the Model Context Protocol, community-built servers, and additional resources to enhance your LLM tool capabilities.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• Model Context Protocol for the specification and examples
• Ollama for the local LLM runtime
• Rich for the terminal user interface

---

Made with ❤️ by jonigl