mcp-client-for-ollama
byjonigl· 2 MCP servers
---
How to install mcp-client-for-ollama?
jonigl/mcp-client-for-ollama
$git clone https://github.com/jonigl/mcp-client-for-ollamaInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install mcp-client-for-ollama by running `git clone https://github.com/jonigl/mcp-client-for-ollama`, then use it for the current task and follow its documentation at https://github.com/jonigl/mcp-client-for-ollama.
README.md
| 1 | <p align="center"> |
| 2 | <img src="https://github.com/jonigl/mcp-client-for-ollama/blob/main/misc/ollmcp-logo-512.png?raw=true" width="256" /> |
| 3 | </p> |
| 4 | <p align="center"> |
| 5 | <i>A simple yet powerful Python client for interacting with Model Context Protocol (MCP) servers using Ollama, allowing you to harness local LLMs for advanced tool execution.</i> |
| 6 | </p> |
| 7 | <p align="center"> |
| 8 | <b>English</b> | <a href="README.zh-CN.md">简体中文</a> | <a href="README.es.md">Español</a> |
| 9 | </p> |
| 10 | |
| 11 | --- |
| 12 | |
| 13 | # MCP Client for Ollama (ollmcp) |
| 14 | |
| 15 |  |
| 16 | [](https://www.python.org/downloads/) |
| 17 | [](https://pypi.org/project/ollmcp/) |
| 18 | [](https://pypi.org/project/mcp-client-for-ollama/) |
| 19 | [](https://github.com/jonigl/mcp-client-for-ollama/actions/workflows/ci.yml) |
| 20 | |
| 21 | <p align="center"> |
| 22 | <sub>Sponsored by</sub> |
| 23 | <br> |
| 24 | <a href="https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=mcp-client-for-ollama"> |
| 25 | <picture> |
| 26 | <source media="(prefers-color-scheme: dark)" srcset="https://github.com/jonigl/mcp-client-for-ollama/blob/main/misc/atlascloud-logo-dark.png?raw=true"> |
| 27 | <img src="https://github.com/jonigl/mcp-client-for-ollama/blob/main/misc/atlascloud-logo.png?raw=true" alt="Atlas Cloud" height="20"> |
| 28 | </picture> |
| 29 | </a> |
| 30 | <br> |
| 31 | <sub>Learn how to use Atlas Cloud with ollmcp in the <a href="#sponsors">Sponsors</a> section</sub> |
| 32 | </p> |
| 33 | |
| 34 | <p align="center"> |
| 35 | <img src="https://raw.githubusercontent.com/jonigl/mcp-client-for-ollama/v0.27.0/misc/ollmcp-demo.gif" alt="MCP Client for Ollama Demo"> |
| 36 | </p> |
| 37 | <p align="center"> |
| 38 | <a href="https://asciinema.org/a/875917" target="_blank">🎥 Watch this demo as an Asciinema recording</a> |
| 39 | </p> |
| 40 | |
| 41 | ## Table of Contents |
| 42 | |
| 43 | - [Overview](#overview) |
| 44 | - [Features](#features) |
| 45 | - [Requirements](#requirements) |
| 46 | - [Quick Start](#quick-start) |
| 47 | - [Installation Options](#installation-options) |
| 48 | - [Troubleshooting](#troubleshooting) |
| 49 | - ✨**NEW** [Managing MCP Servers via CLI](#managing-mcp-servers-via-cli) |
| 50 | - [mcp add options](#mcp-add-options) |
| 51 | - [Scopes](#scopes) |
| 52 | - [Command-line Arguments](#command-line-arguments) |
| 53 | - [MCP Server Configuration](#mcp-server-configuration) |
| 54 | - ✨**NEW** [Inference Provider Configuration](#inference-provider-configuration) |
| 55 | - [General Options](#general-options) |
| 56 | - ✨**NEW** [Supported Inference Providers](#supported-inference-providers) |
| 57 | - [API key resolution order](#api-key-resolution-order) |
| 58 | - [Usage Examples](#usage-examples) |
| 59 | - [How Tool Calls Work](#how-tool-calls-work) |
| 60 | - [Agent Mode](#agent-mode) |
| 61 | - [Interactive Commands](#interactive-commands) |
| 62 | - [MCP Tools](#mcp-tools) |
| 63 | - [MCP Prompts](#mcp-prompts) |
| 64 | - [MCP Resources](#mcp-resources) |
| 65 | - ✨**NEW** [Answer Display Modes](#answer-display-modes) |
| 66 | - [Input Mode](#input-mode) |
| 67 | - [Model Selection](#model-selection) |
| 68 | - [Advanced Model Configuration](#advanced-model-configuration) |
| 69 | - ✨**NEW** [Thinking Mode and Reasoning Effort](#thinking-mode-and-reasoning-effort) |
| 70 | - [Server Reloading for Development](#server-reloading-for-development) |
| 71 | - [Human-in-the-Loop (HIL) Tool Execution](#human-in-the-loop-hil-tool-execution) |
| 72 | - [Human-in-the-Loop (HIL) Configuration](#human-in-the-loop-hil-configuration) |
| 73 | - [Performance Metrics](#performance-metrics) |
| 74 | - [History Management](#history-management) |
| 75 | - [Autocomplete and Prompt Features](#autocomplete-and-prompt-features) |
| 76 | - [Typer Shell Autocompletion](#typer-shell-autocompletion) |
| 77 | - [FZF-style Autocomplete](#fzf-style-autocomplete) |
| 78 | - [MCP Prompts Autocomplete](#mcp-prompts-autocomplete) |
| 79 | - [Contextual Prompt](#contextual-prompt) |
| 80 | - [Configuration Management](#configuration-management) |
| 81 | - ✨** |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
