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 local LLMs (via Ollama) to interact with external tools and data sources using the Model Context Protocol (MCP). It bridges the gap between local model inference and the ability to execute code, read files, or access APIs through a standardized protocol, providing a safe, interactive environment for tool-using agents.

How it works

The application acts as a TUI (Terminal User Interface) that connects to one or more MCP servers via various transport methods (STDIO, SSE, or Streamable HTTP). It manages the communication between the LLM and these servers, handling tool calls, prompt templates, and resource retrieval. It includes a "Human-in-the-Loop" safety mechanism where users must approve tool executions before they run, and an "Agent Mode" for iterative tool execution loops.

Who it’s for

It is designed for developers and AI enthusiasts who want to use local LLMs for autonomous or semi-autonomous tasks, test MCP servers, or build agentic workflows without needing to write custom integration code for every tool.

Highlights

  • Multi-Server Support: Connect to multiple MCP servers simultaneously across different transport types.
  • Agent Mode: Supports iterative tool execution with configurable loop limits.
  • Human-in-the-Loop (HIL): Review and approve tool executions for enhanced safety.
  • Broad Provider Support: While optimized for Ollama, it also supports OpenAI-compatible providers like DeepSeek and OpenRouter.
  • Thinking Mode: Visible thought processes for reasoning models (e.g., DeepSeek-R1).
  • Rich TUI: Features fuzzy autocomplete, streaming responses, and JSON syntax highlighting for tool outputs.

Related

  • Project
    ggozad/oterm

    A terminal client for interacting with multiple AI providers including Ollama, OpenAI, and Anthropic via pydantic-ai.

  • Project
    nwiizo/tfmcp

    A command-line tool that implements the Model Context Protocol (MCP) to allow LLMs to manage and operate Terraform environments, including configuration analysis and infrastructure deployment.

  • Project
    nakasyou/local-mcp

    A Model Context Protocol (MCP) server that exposes local filesystem and command execution capabilities to AI agents with built-in sandboxing and user approval workflows.

  • Project
    apify/mcpc

    A universal CLI client for the Model Context Protocol (MCP) that enables AI agents and developers to interact with MCP servers via shell commands.

  • 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.