MCP Client for Ollama (ollmcp)
@jonigl
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
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.
Frequently asked questions
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.
Basic information
More AI & Agents MCP servers
Just Prompt - A lightweight MCP server for LLM providers
dislerjust-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
🛡️ A.I.G（AI-Infra-Guard）
TencentA full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
Agentery
ntlgncFree MCP for live and historical pricing for 13,000+ agents and MCPs. Never knowingly pay too much... or charge too little. Know the going rate. https://agentery.com.
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
Comments