MCP Client for Ollama (ollmcp) is a text-based user interface (TUI) client for interacting with MCP servers using Ollama. Features include agent mode, multi-server, model switching, streaming responses, tool management, human-in-the-loop, thinking mode, model params config, MCP prompts, custom system prompt and saved preferences. Built for developers working with local LLMs.
This update delivers a cleaner, more consistent command experience in the Ollama MCP client, with improved prompt routing, better autocomplete, and clearer startup diagnostics.
What changed for users
Commands are now slash-first.
Use commands like /help, /quit, /model, /tools, and /prompts.
The client now clearly separates normal chat input from slash commands and prompt calls.
Short aliases are supported for common actions (for example /h, /q, /hil).
Prompt resolution is more robust, including support for qualified prompt references such as /server:prompt_name.
Ambiguous prompt names now return clearer guidance and candidate options.
Slash autocomplete was improved with clearer command and prompt suggestions.
Completion UI badges and terminal rendering were improved, including better tmux behavior.
Startup preflight checks for Ollama connectivity were improved.
Missing-tools and connection failure messages are now more actionable.
This refactor is backed by expanded automated test coverage for routing, commands, prompts, quit handling, and completion behavior.
Important compatibility note
If you previously used bare commands, switch to slash commands.