mcp-devops-on-prem

MCP DevOps On-Premise

MCP DevOps On-Premise is a Model Context Protocol (MCP) server which allows you to use AI tools, such as Claude, GitHub Copilot, Cursor, and others, directly with your DevOps On-Premise environment.

With this MCP server, you can let your AI assistant work with your DevOps data and actions, for example around work items, wiki pages, pull requests, repositories, and related review workflows.

Why this MCP server is necessary?

AI assistants cannot access external systems and act on external data without tools/connectors. In MCP-based setups, those capabilities are provided through MCP servers.

This MCP server provides that bridge to DevOps On-Premise so your assistant can:

This project is that bridge layer between your AI agent and your DevOps Server.

Without this MCP server (or another equivalent integration), your assistant usually cannot:

Also, Microsoft states in its Azure DevOps MCP - FAQ that their MCP server supports Azure DevOps Services only and they currently do not plan Azure DevOps On-Prem support. This MCP server fills that gap for on-prem environments.

What makes this server stand out

One of the most important features of this server is NTLM authentication support, which is required by many on-premises and enterprise environments where users authenticate with their Windows domain credentials, either directly or over VPN. Most MCP servers for Azure DevOps target only cloud-hosted Azure DevOps Services with token-based auth and cannot connect to these environments.

This means you can use this server in environments where:

What this server provides

Documentation

Project