MCP.so
Sign In

MCP Client for Ollama (ollmcp)

@jonigl

Repository

About MCP Client for Ollama (ollmcp)

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 pre

#open-source#ai#mcp#sse#model-selection#stdio#command-line-tool#terminal-based#pypi-package#tool-management#chat-interface#llm#generative-ai#local-llm#ollama#model-context-protocol#mcp-server#mcp-client

Basic information

Category

AI & Agents

License

MIT

Runtime

python

Transports

stdio

Publisher

jonigl

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-client-for-ollama": {
      "command": "uv",
      "args": [
        "tool",
        "install",
        "--upgrade",
        "ollmcp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Client for Ollama (ollmcp)?

MCP Client for Ollama (ollmcp) is a Python terminal application that connects local Ollama LLMs to one or more Model Context Protocol (MCP) servers. It supports core MCP primitives—tools, prompts, and resources—and is designed for developers building, testing, or exploring MCP-powered workflows with local AI models.

How to use MCP Client for Ollama (ollmcp)?

Install the package via uv tool install --upgrade ollmcp or pip install --upgrade ollmcp. Add an MCP server with ollmcp mcp add <name> -- <command>, then launch the client by running ollmcp. Use /help inside the interactive session for available commands.

Key features of MCP Client for Ollama (ollmcp)

  • Agent Mode with iterative tool execution and configurable loop limits
  • Multi-Server Support and multiple transport types (STDIO, SSE, Streamable HTTP)
  • Human-in-the-Loop (HIL) tool execution for safety
  • Rich terminal interface with streaming responses and fuzzy autocomplete
  • Dynamic model switching and advanced model parameter configuration
  • Server hot-reloading and conversation history management
  • Support for Ollama (default) and OpenAI-compatible LLM providers

Use cases of MCP Client for Ollama (ollmcp)

  • Connect local Ollama models to existing MCP tool servers for automated tasks
  • Prototype and debug MCP servers during development with hot-reloading
  • Run multi-step agent workflows with strict human approval on tool calls
  • Experiment with different LLM providers and model parameters in a single session

FAQ from MCP Client for Ollama (ollmcp)

What are the runtime requirements?

Python 3.11 or newer, Ollama running locally, and the UV package manager (recommended). pip installation is also supported.

How do I fix a "Could not find a version that satisfies the requirement ollmcp" error?

This usually means your Python version is older than 3.11. Use uv tool install --upgrade ollmcp (uv auto-selects a compatible Python) or install with a Python 3.11+ interpreter.

Can I use cloud-hosted models instead of a local Ollama instance?

Yes. Ollama Cloud is supported, and you can also use OpenAI-compatible providers such as OpenAI, OpenRouter, and DeepSeek.

What types of MCP servers does ollmcp connect to?

It supports STDIO, SSE, and Streamable HTTP transport types. It can connect to multiple servers simultaneously and automatically discovers existing Claude MCP configurations.

How does tool safety work?

Human-in-the-Loop (HIL) mode lets you review and approve tool executions before they run. You can also enable/disable specific tools or entire servers during a chat session.

Comments

More AI & Agents MCP servers

1Panel

1Panel-dev

🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.

36.1K

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K

21st.dev Magic AI Agent

21st-dev

It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

5.3K