Vibe Coding Discover

MCP

mcp-client-for-ollama

View on GitHub

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.

★ 828129 forksPythonMITjonigl

A Python terminal client that connects Ollama and compatible LLM providers to one or more MCP servers. Supports agentic tool execution, prompts, resources, streaming, model configuration, and approval of tool calls.

Use Cases

Connect local LLMs to MCP serversRun iterative tool-using agents from a terminalReview and approve tool calls before executionExplore and invoke MCP prompts and resourcesTest MCP servers over stdio, SSE, or Streamable HTTPSwitch models and configure inference parameters

Built With

Language
Python
Frameworks
Model Context Protocol (MCP) · Ollama · Typer · prompt-toolkit

Tags

MCP client · Ollama · TUI · agent mode · tool calling · human-in-the-loop · MCP tools · MCP prompts · MCP resources · multi-server · streaming · local LLM