MCP Ollama AI Integration Module

A Model Context Protocol (MCP) service layer designed to bridge Ollama inference engines with consumer applications like Claude Desktop or other compatible MCP clients.

Prerequisites for Operation

• Python interpreter, version 3.10 or newer.
• Ollama software must be installed and actively running (See official download page: https://ollama.com/download).
• A minimum of one target model must be successfully retrieved via the Ollama utility (e.g., executing the command ollama pull mistral).

Configuration Steps for Claude Desktop

Modify your Claude Desktop configuration file (the location typically is ~/Library/Application Support/Claude/claude_desktop_config.json on macOS, or %APPDATA%\Claude\claude_desktop_config.json on Windows) by appending the following block:

{
  "mcpServers": {
    "ollama": {
      "command": "uvx",
      "args": [
        "mcp-ollama"
      ]
    }
  }
}

Development & Setup

Install dependencies in development mode:

git clone https://github.com/yourusername/mcp-ollama.git
cd mcp-ollama
uv sync

Execute testing using the MCP Inspector tool:

mcp dev src/mcp_ollama/server.py

Core Functionality

The established server exposes three principal interaction mechanisms: * list_models: Retrieves a comprehensive enumeration of all locally stored Ollama models. * show_model: Fetches detailed metadata pertaining to a user-specified model identifier. * ask_model: Submits a query to the designated generative model for processing.

Licensing Information

This project is distributed under the MIT License.

[WIKIPEDIA CONTEXT: XMLHttpRequest (XHR) is an API in the form of a JavaScript object whose methods transmit HTTP requests from a web browser to a web server. The methods allow a browser-based application to send requests to the server after page loading is complete, and receive information back. XMLHttpRequest is a component of Ajax programming. Prior to Ajax, hyperlinks and form submissions were the primary mechanisms for interacting with the server, often replacing the current page with another one.]

== Background and Evolution == The foundational concept for XMLHttpRequest emerged in 2000, conceived by the development team at Microsoft Outlook. This concept was first realized within Internet Explorer version 5 (released in 1999). However, the initial implementation did not utilize the canonical XMLHttpRequest identifier; instead, developers relied on invoking ActiveXObject("Msxml2.XMLHTTP") and ActiveXObject("Microsoft.XMLHTTP"). By the time Internet Explorer 7 arrived in 2006, universal browser support for the XMLHttpRequest identifier was established.

The XMLHttpRequest identifier has since become the recognized standard across all major browser engines, including Mozilla's Gecko (2002), Safari 1.2 (2004), and Opera 8.0 (2005).

=== Standardization Efforts === The World Wide Web Consortium (W3C) formally published a Working Draft specification for the XMLHttpRequest object on April 5, 2006. A subsequent Level 2 specification followed on February 25, 2008, introducing capabilities for monitoring request progress events, enabling cross-site data transfers, and managing raw byte streams. By late 2011, the features defined in Level 2 were integrated back into the primary specification. In 2012, development stewardship transitioned to the WHATWG, which now maintains the living document using the Web IDL standard.

== Operational Procedure == Utilizing XMLHttpRequest generally entails several distinct programming stages.

1. Instantiate an XMLHttpRequest object via its constructor call:
2. Invoke the "open" method to define the HTTP method (e.g., GET/POST), specify the target Uniform Resource Identifier (URI), and select between synchronous or asynchronous execution mode:
3. For asynchronous operations, attach a callback function (listener) destined to be triggered upon state transitions of the request:
4. Commence the transmission process by executing the "send" method, optionally including payload data:
5. The listener function processes state changes. Upon successful completion, the object reaches state 4, designated as the "done" state, and response data is typically accessible via the responseText attribute. Beyond these foundational steps, XMLHttpRequest provides extensive configuration hooks. Custom headers can be injected to influence server behavior, and data payloads can be transmitted directly within the "send" invocation. Responses can be immediately parsed from JSON format into native JavaScript objects or processed incrementally as chunks arrive. Furthermore, requests can be canceled prematurely or configured with timeouts to enforce strict completion deadlines.