mcp-devops-onpremise 0.2.0

MCP server for on-premises Azure DevOps — browse repositories, pull requests, work items, and wikis.

MCP DevOps On-Premise

Model Context Protocol MCP server for on-premises Azure DevOps that lets AI assistants browse repositories, review pull requests, manage work items, and interact with wikis.

Overview • Getting Started • Installation Guide • Updating • Available Tools • Development

Overview

Many organizations use on-premise DevOps solutions such as TFS or Azure DevOps Server in their projects. Integrating these systems with modern agentic AI tools and LLMs can be difficult. The official Microsoft Azure DevOps MCP server does not support these environments and is unlikely to support them in the future.

This MCP server closes that gap and enables smooth integration with on-premise DevOps systems.

Key Advantages

• Supports typical on-prem DevOps authentication: NTLM (Windows login/password) and Personal Access Tokens (PAT).
• Enables secure access to on-prem DevOps systems from MCP-compatible AI tools such as GitHub Copilot, Claude Desktop, Cursor, Windsurf, and others.
• Works in restricted or offline environments without exposing sensitive data to external services.
• Retrieves commit diffs with clear added/removed lines, similar to the DevOps UI.
• Helps keep and track project documentation alongside code changes.
• Automates common tasks such as work item management and code review processes.

Getting Started

Quick Install

Prerequisites: Python 3.10+ and uv are required. If not yet installed, see Prerequisites in the Installation Guide below.

Click one of the buttons below to install directly in your IDE — you will be prompted for credentials:

For other platforms, see Manual Installation below.

Manual Installation

For the server command and environment variable settings used in the steps below, see Configuration in the Installation Guide.

VS Code

Follow the MCP install guide, use the configuration below.

After installation, the devops-onprem MCP server will be available for use with your GitHub Copilot agent in VS Code.

VS Code Insiders

Follow the MCP install guide, use the configuration below.

After installation, the devops-onprem MCP server will be available for use with your GitHub Copilot agent in VS Code Insiders.

Visual Studio

1. Open Visual Studio
2. Navigate to the GitHub Copilot Chat window
3. Click the tools icon (🛠️) in the chat toolbar
4. Click the + "Add Custom MCP Server" button to open the "Configure MCP server" dialog
5. Fill in the configuration:
   • Server ID: devops-onprem
   • Type: Select stdio from the dropdown
   • Command (with optional arguments): uvx mcp-devops-onpremise
   • Envisronment Variables: add like described in the Configuration chapter.
6. Click "Save" to add the server

For detailed instructions, see the Visual Studio MCP documentation.

Cursor

Go to Cursor Settings -> MCP -> Add new MCP Server. Name to your liking, use command type with the command from the configuration below. You can also verify config or add command like arguments via clicking Edit.

Goose

Go to Advanced settings -> Extensions -> Add custom extension. Name to your liking, use type STDIO, and set the command from the configuration below. Click "Add Extension".

LM Studio

Go to Program in the right sidebar -> Install -> Edit mcp.json. Use the configuration below.

Amp

Add via the Amp VS Code extension settings screen or by updating your settings.json file:

"amp.mcpServers": 
  "devops-onprem": {
    "command": "uvx",
    "args": [
      "mcp-devops-onpremise"
    ],
    "env": {}
  }

Amp CLI Setup:

Add via the amp mcp add command below:

amp mcp add devops-onprem -- uvx mcp-devops-onpremise

Claude Code

Use the Claude Code CLI to add the devops-onprem MCP server:

claude mcp add devops-onprem uvx mcp-devops-onpremise

Claude Desktop

Follow the MCP install guide, use the configuration below.

Codex

Create or edit the configuration file ~/.codex/config.toml and add:

[mcp_servers.devops-onprem]
command = "uvx"
args = ["mcp-devops-onpremise"]

For more information, see the Codex MCP documentation.

Gemini CLI

Follow the MCP install guide, use the configuration below.

OpenCode

Follow the MCP Servers documentation. For example in ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "devops-onprem": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-devops-onpremise"
      ],
      "enabled": true
    }
  }
}

Qodo Gen

Open Qodo Gen chat panel in VSCode or IntelliJ → Connect more tools → + Add new MCP → Paste the configuration below.

Click Save.

Warp

Go to Settings -> AI -> Manage MCP Servers -> + Add to add an MCP Server. Use the configuration below.

Alternatively, use the slash command /add-mcp in the Warp prompt and paste the configuration below.

Windsurf

Follow Windsurf MCP documentation. Use the configuration below.

GitHub Copilot CLI

GitHub Copilot CLI supports adding MCP servers interactively and through a config file.

Option 1: Interactive setup with /mcp add

1. Open GitHub Copilot CLI in interactive mode.
2. Run /mcp add.
3. Enter Server Name: devops-onprem.
4. Choose Server Type:
   • STDIO for command-based servers
   • HTTP for remote servers
5. Fill in command/url settings from the configuration below and set Tools to *.
6. Press Ctrl+S to save.

Option 2: Edit ~/.copilot/mcp-config.json

Use the configuration below.

For more information, see the GitHub Copilot CLI MCP documentation.

GitHub Copilot Coding Agent

GitHub Copilot Coding Agent can use MCP servers to extend its capabilities. Use the configuration below — add it to your repository settings under Copilot > Coding agent.

Add this configuration to your repository settings under Copilot > Coding agent. The "tools": ["*"] setting enables all available tools from the MCP server.

For more information, see the GitHub Copilot Coding Agent MCP documentation.

Installation Guide

Prerequisites

Python 3.10 or later

If Python is not installed on your machine, download it from python.org.

Windows: Check "Add Python to PATH" during installation.
pip is included with Python — no separate install needed.

uv

uv is a fast Python package manager that powers the one-click installs and the ephemeral server launch.

Windows users: Open Command Prompt (cmd) or PowerShell to run all commands in this guide.

pip install uv

More info: uv documentation

Standalone Server Installation (optional)

In most cases you do not need to install the server separately — the IDE integrations in Getting Started handle this automatically via uvx. If you need to run or test the server outside an IDE:

Ephemeral (recommended, no permanent install):

uvx mcp-devops-onpremise

Permanent install:

pip install mcp-devops-onpremise

Authentication

The server supports three authentication methods. Start with NTLM (username + password) if you connect via VPN or are on a corporate network. Use PAT if it is available and works in your environment.

Option 1: Username + Password (NTLM — most common for on-prem/VPN)

Typical for on-premises Azure DevOps Server accessed via VPN or Windows Auth.

Variable	Value
DEVOPS_USERNAME	DOMAIN\your-username
DEVOPS_PASSWORD	Your Windows / Active Directory password

Option 2: Personal Access Token (PAT)

PAT is simpler to configure but may not work if your on-prem server blocks token-based access or requires VPN + NTLM.

To create a PAT: open your DevOps profile → Personal access tokens → New token. See: Microsoft docs - Create a PAT

Variable	Value
DEVOPS_PAT	Your personal access token
DEVOPS_USERNAME	(optional) Your username

Option 3: OAuth Bearer Token (advanced / CI/CD only)

OAuth Bearer tokens work only if your on-prem Azure DevOps Server has OAuth 2.0 configured — uncommon in standard on-prem setups. Mainly useful for Azure DevOps Services (cloud) or automated pipelines that receive short-lived tokens from an identity provider.

Variable	Value
DEVOPS_TOKEN	Your OAuth Bearer token

If you are unsure whether OAuth is available, use NTLM or PAT instead.

MD4 Support (NTLM only, optional)

NTLM authentication requires the MD4 hash algorithm, which is not included in all Python environments. If you encounter an MD4-related error, install pycryptodome:

pip install pycryptodome

Skip this step if you use PAT or OAuth.

Configuration

The DEVOPS_API_URL must point to your full project URL:

https://<your-devops-server>/<organization>/<project>

With NTLM (username + password)

{
  "mcpServers": {
    "devops-onprem": {
      "command": "uvx",
      "args": ["mcp-devops-onpremise"],
      "env": {
        "DEVOPS_API_URL": "https://your-devops-server/your-organization/your-project",
        "DEVOPS_USERNAME": "DOMAIN\\your-username",
        "DEVOPS_PASSWORD": "your-password"
      }
    }
  }
}

With PAT

{
  "mcpServers": {
    "devops-onprem": {
      "command": "uvx",
      "args": ["mcp-devops-onpremise"],
      "env": {
        "DEVOPS_API_URL": "https://your-devops-server/your-organization/your-project",
        "DEVOPS_PAT": "your-personal-access-token"
      }
    }
  }
}

If you used a permanent install, replace "command": "uvx" with "command": "mcp-devops-onpremise" and remove the "args" line.

Updating

Check the current installed version

If you installed permanently (Option B):

mcp-devops-onpremise --version

Check if a newer version is available

Visit the releases page on GitHub or the CHANGELOG.

Update to the latest version

If you use uvx (Option A): uvx always fetches the latest version from PyPI automatically — no action needed.

If you installed permanently (Option B):

pip install --upgrade mcp-devops-onpremise

Available Tools

Pull Requests

Tool	Description	Read-only
devops_pull_request_get	Retrieve a pull request by ID, including linked work items and commit SHAs for diffing	✅
devops_pull_request_list_threads	Returns a hierarchical list of non-deleted comment threads and their text comments	✅
devops_pull_request_list_thread_comments	List non-deleted text comments in a specific thread	✅
devops_pull_request_create_comment	Create a new thread with an initial comment (general or inline on a file/line)	❌
devops_pull_request_reply_comment	Reply to an existing comment thread	❌
devops_pull_request_update_thread	Update the status of a comment thread	❌
devops_pull_request_update_comment	Update the text of an existing comment	❌
devops_pull_request_delete_comment	Delete a comment from a pull request thread	❌

Repositories

Tool	Description	Read-only
devops_repository_list	List all repositories in the project	✅
devops_repository_get	Retrieve repository details by name or ID	✅
devops_repository_commit_changes	List files changed in a specific commit	✅
devops_repository_diffs_commits	Get the difference between two commits (changed file paths)	✅
devops_repository_item_content	Get raw file content at a specific commit or branch	✅
devops_get_item_content_diff	Get line-level textual diff of a file between two commits (added lines prefixed +, removed -)	✅

Work Items

Tool	Description	Read-only
devops_work_item_get	Retrieve a work item (PBI, bug, task) by numeric ID. Returns a compact object with key fields, attachments (files and inline images), and linked items (work items, pull requests, commits)	✅
devops_work_item_attachment_get	Download a work item attachment by its GUID, either saving locally or returning base64-encoded content	✅

Wiki

Tool	Description	Read-only
devops_wiki_page_get_by_url	Get wiki page metadata (id, path) and optional content by its URL	✅
devops_wiki_page_create_or_update	Create or update a wiki page under a specified parent page	❌
devops_wiki_page_update	Update an existing wiki page by ID	❌
devops_wiki_page_delete	Delete an existing wiki page by ID	❌

Development

# Install dev dependencies
uv sync --group dev

# Run linting
uv run ruff check src/
uv run black --check src/

# Run tests
uv run pytest tests/