jonigl/mcp-client-for-ollama

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.

What it solves

ollmcp is a terminal-based client that allows users to connect local Large Language Models (LLMs) via Ollama to Model Context Protocol (MCP) servers. It bridges the gap between local LLMs and external tools, prompts, and resources, providing a controlled environment to execute advanced tool-calling tasks without requiring the user to write code.

How it works

The application acts as a TUI (Terminal User Interface) that connects to one or more MCP servers using various transport types (STDIO, SSE, or Streamable HTTP). It supports the core MCP primitives—tools, prompts, and resources—and integrates them with LLM providers. When a model requests a tool call, the client manages the execution and can be configured for "Agent Mode" (iterative tool execution) or "Human-in-the-Loop" (requiring manual approval before execution).

Who it’s for

It is designed for harness engineers, developers, and AI enthusiasts who want to use local LLMs for tool execution, test MCP servers, or build agentic workflows in a terminal environment.

Highlights

  • Agent Mode: Supports iterative tool execution with configurable loop limits.
  • Multi-Server Support: Connects to multiple MCP servers simultaneously across different transport types.
  • Human-in-the-Loop (HIL): Provides safety controls by requiring user review and approval for tool executions.
  • Broad Provider Support: Works with Ollama by default, but also supports OpenAI-compatible providers like OpenRouter, DeepSeek, and Atlas Cloud.
  • Advanced Model Control: Offers fine-tuning for 15+ parameters, including context window size and temperature.
  • Thinking Mode: Supports visible reasoning processes for compatible models (e.g., DeepSeek-R1).
  • Developer Friendly: Includes hot-reloading for MCP servers, fuzzy autocomplete for commands, and detailed performance metrics.

Related

  • Project
    daodao97/chatmcp

    A cross-platform AI chat client that integrates with the Model Context Protocol (MCP) to connect LLMs with external data sources and tools.

  • Project
    paulrobello/parllama

    A TUI application for managing and chatting with local Ollama models and major cloud LLM providers in a single terminal interface.

  • Project
    ggozad/oterm

    oterm is a terminal client that provides a TUI for interacting with LLM providers like Ollama, OpenAI, and Anthropic.

  • Dispatch
    Production Use Cases of Model Context Protocol (MCP): Real‑World Benefits and Patterns

    MCP is being used in production across a wide range of domains—from voice agents and enterprise SaaS to personal data archives—because it standardizes tool access, handles authentication, and lets non‑technical users interact with AI without writing code.

  • Project
    maquina-app/rails-mcp-server

    A Ruby implementation of the Model Context Protocol (MCP) server that allows LLMs to analyze and interact with Rails projects through structured tools and documentation.