MCP ExplorerExplorer

Mcp Ollama Link

@punkpeyeon a year ago
3 MIT
FreeCommunity
AI Systems
Save your token limit by offloading compute to your local system. Supports Deepseek.

Overview

What is Mcp Ollama Link

mcp-ollama-link is an MCP server that allows users to save their token limits by offloading compute tasks to their local systems. It supports Deepseek and enables the initiation of Ollama queries via Claude.

Use cases

Use cases for mcp-ollama-link include managing personal notes, summarizing research articles, creating study aids, and facilitating collaborative note-taking among teams.

How to use

To use mcp-ollama-link, install it on your local system by configuring the Claude Desktop application. You can add notes using the ‘add-note’ tool and summarize them with the ‘summarize-notes’ prompt.

Key features

Key features of mcp-ollama-link include a custom note storage system with a note:// URI scheme, the ability to create summaries of stored notes with customizable detail levels, and a tool for adding new notes.

Where to use

mcp-ollama-link can be used in various fields such as personal knowledge management, note-taking applications, and any scenario where summarization of information is required.

Content

mcp-ollama-link MCP server

Initiate Ollama queries via Claude.

Components

Resources

The server implements a simple note storage system with:

  • Custom note:// URI scheme for accessing individual notes
  • Each note resource has a name, description and text/plain mimetype

Prompts

The server provides a single prompt:

  • summarize-notes: Creates summaries of all stored notes
    • Optional “style” argument to control detail level (brief/detailed)
    • Generates prompt combining all current notes with style preference

Tools

The server implements one tool:

  • add-note: Adds a new note to the server
    • Takes “name” and “content” as required string arguments
    • Updates server state and notifies clients of resource changes

Configuration

[TODO: Add configuration details specific to your implementation]

Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration ``` "mcpServers": { "mcp-ollama-link": { "command": "uv", "args": [ "--directory", "C:\Users\ktrua\source\repos\mcp-ollama-link", "run", "mcp-ollama-link" ] } } ```
Published Servers Configuration ``` "mcpServers": { "mcp-ollama-link": { "command": "uvx", "args": [ "mcp-ollama-link" ] } } ```

Development

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:
uv sync
  1. Build package distributions:
uv build

This will create source and wheel distributions in the dist/ directory.

  1. Publish to PyPI:
uv publish

Note: You’ll need to set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN
  • Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging
experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory C:\Users\ktrua\source\repos\mcp-ollama-link run mcp-ollama-link

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers