Lightweight MCP client that uses a local Ollama LLM to query multiple MCP servers defined in config.json
Overview
What is MCP-Ollama Client?
MCP-Ollama Client is a lightweight command-line chat client that operates entirely offline using a local LLM via Ollama to interact with multiple Model-Context-Protocol (MCP) servers defined in a configuration file.
How to use MCP-Ollama Client?
To use MCP-Ollama Client, clone the repository, set up the environment, pull a local model, configure the config.json file, and run the client.
Key features of MCP-Ollama Client?
- Runs entirely offline with a local LLM.
- Supports multiple MCP servers defined in a single
config.json. - Collision-free tool names to avoid naming conflicts.
Use cases of MCP-Ollama Client?
- Interacting with various databases like Postgres.
- Accessing filesystem tools locally.
- Running multiple MCP servers simultaneously without cloud dependencies.
FAQ from MCP-Ollama Client?
- Can I run MCP-Ollama Client without an internet connection?
Yes! MCP-Ollama Client is designed to run entirely offline.
- What programming language is used for MCP-Ollama Client?
MCP-Ollama Client is developed in Python.
- How do I add more MCP servers?
You can add more servers by modifying the
config.jsonfile without changing the client code.