mcp-ollama-agent
A TypeScript example showcasing the integration of Ollama with the Model Context Protocol (MCP) servers. This project provides an interactive command-line interface for an AI agent that can utilize the tools from multiple MCP Servers..
Documentation
TypeScript MCP Agent with Ollama Integration
This project demonstrates integration between Model Context Protocol (MCP) servers and Ollama, allowing AI models to interact with various tools through a unified interface.
✨ Features
- Supports multiple MCP servers (both uvx and npx tested)
- Built-in support for file system operations and web research
- Easy configuration through `mcp-config.json` similar to `claude_desktop_config.json`
- Interactive chat interface with Ollama integration that should support any tools
- Standalone demo mode for testing web and filesystem tools without an LLM
🚀 Getting Started
1. Prerequisites:
# For filesystem operations
npm install -g @modelcontextprotocol/server-filesystem
# For web research
npm install -g @mzxrai/mcp-webresearch2. Clone and install:
git clone https://github.com/ausboss/mcp-ollama-agent.git
cd mcp-ollama-agent
npm install3. Configure your tools and tool supported Ollama model in `mcp-config.json`:
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["@modelcontextprotocol/server-filesystem", "./"]
},
"webresearch": {
"command": "npx",
"args": ["-y", "@mzxrai/mcp-webresearch"]
}
},
"ollama": {
"host": "http://localhost:11434",
"model": "qwen2.5:latest"
}
}4. Run the demo to test filesystem and webresearch tools without an LLM:
npx tsx ./src/demo.ts5. Or start the chat interface with Ollama:
npm start⚙️ Configuration
- MCP Servers: Add any MCP-compatible server to the `mcpServers` section
- Ollama: Configure host and model (must support function calling)
- Supports both Python (uvx) and Node.js (npx) MCP servers
💡 Example Usage
This example used this model qwen2.5:latest
Chat started. Type "exit" to end the conversation.
You: can you use your list directory tool to see whats in test-directory then use your read file tool to read it to me?
Model is using tools to help answer...
Using tool: list_directory
With arguments: { path: 'test-directory' }
Tool result: [ { type: 'text', text: '[FILE] test.txt' } ]
Assistant:
Model is using tools to help answer...
Using tool: read_file
With arguments: { path: 'test-directory/test.txt' }
Tool result: [ { type: 'text', text: 'rosebud' } ]
Assistant: The content of the file `test.txt` in the `test-directory` is:
rosebud
You: thanks
Assistant: You're welcome! If you have any other requests or need further assistance, feel free to ask.System Prompts
Some local models may need help with tool selection. Customize the system prompt in `ChatManager.ts` to improve tool usage.
🤝 Contributing
Contributions welcome! Feel free to submit issues or pull requests.
Frequently asked questions
What is mcp-ollama-agent?
mcp-ollama-agent is A TypeScript example showcasing the integration of Ollama with the Model Context Protocol (MCP) servers. This project provides an interactive command-line interface for an AI agent that can utilize the tools from multiple MCP Servers..
How do I install mcp-ollama-agent?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-ollama-agent open source?
Yes — it is hosted on GitHub at https://github.com/ausboss/mcp-ollama-agent and has 27 stars.
Related MCP tools
Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Built for the Model Context Protocol to enhance AI capabilities.
Mcp-use is the easiest way to interact with mcp servers with custom agents TypeScript-based implementation. Trusted by 8100+ developers.
🐬DeepChat - A smart assistant that connects powerful AI to your personal world for the Model Context Protocol. Enhance AI assistants with powerful integrations
Code search MCP for Claude Code. Make entire codebase the context for any coding agent. TypeScript-based implementation. Trusted by 4100+ developers.
A Unified MCP Server Management App TypeScript-based implementation. Trusted by 800+ developers. Trusted by 800+ developers.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP