convez.ai
MCP ServerDevOps & InfraestruturaIntermediário
zwitbaum

MCP DevOps On-Premise

zwitbaum/mcp-devops-on-prem

Conecte IA ao Azure DevOps on-premise com NTLM e automação DevOps

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que integra Azure DevOps on-premise (TFS) com assistentes de IA, permitindo navegação de repositórios, revisão de pull requests, gerenciamento de work items e wikis. Suporta autenticação NTLM para ambientes corporativos com credenciais de domínio Windows, ideal para organizações sem acesso à nuvem.

Instalação

$npx convez-ai zwitbaum/mcp-devops-on-prem

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
6
Forks
1
Acompanhando
1
Saúde
42%
Último commit
há 1 semana
Versão
v2.2.0
Issues abertas
1
Contribuidores
1

Casos de uso

  • Automação de revisão de código e gerenciamento de PRs em TFS on-premise
  • Rastreamento e atualização de work items via agentes de IA
  • Integração de documentação de projetos com mudanças de código
  • Acesso seguro a DevOps corporativo via Claude Desktop ou GitHub Copilot

Veredito

Solução técnica robusta que preenche uma lacuna real: suporte NTLM para DevOps on-premise que outras ferramentas ignoram. Produção-ready para empresas em ambientes restritos, mas requer configuração manual de credenciais e conhecimento de arquitetura DevOps.

README

A tradução para o português deste README ainda está na fila.

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.

License: MIT PyPI - Version

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.

This project is under active development, with features continuously added to meet current requirements. Community needs are highly valued — if you miss any features, please submit an Issue. User-requested features are fast-tracked and will be prioritized and added as soon as possible.

Key Advantages

One of the most important features of this MCP server is NTLM authentication support. NTLM is required by many on-premises and enterprise environments where users authenticate with 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.

  • NTLM authentication (Windows domain credentials) for on-prem and VPN-based setups where no other auth method works.
  • PAT and OAuth bearer token authentication as alternatives when available.
  • 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

Prerequisites

Python 3.10+ and uv are required. If not yet installed, see installation guide.

Quick Install

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

Install in VS Code Install in VS Code Insiders Install in Cursor

For other platforms, see Manual Installation in the Getting Started guide.

Manual Installation

The MCP server can be installed manually in the following AI tools: VS Code, Visual Studio, Cursor, Goose, LM Studio, Amp, Claude Code, Claude Desktop, Codex, Gemini CLI, OpenCode, Qodo Gen, Warp, Windsurf, GitHub Copilot CLI, GitHub Copilot Coding Agent, and others.

For step-by-step instructions, see Manual Installation in the Getting Started guide.

Configuration

The DEVOPS_API_URL must point to your full project URL:

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

The server supports three authentication methods. If you are unsure which one to use, start with NTLM because it is the most common for on-prem/VPN setups.

MethodDescription
NTLM (username + password)Most common for on-prem/VPN. Usually the simplest first setup and best fallback if other options fail.
PAT (Personal Access Token)Use when PAT is enabled and allowed. Tokens can expire, and token-based auth may be blocked by policy. Advantage: you do not store your account password in config.
OAuth Bearer TokenAdvanced option for CI/CD pipelines. Requires OAuth 2.0 configured on your DevOps Server and a token source defined by your administrators.

For detailed setup instructions for each method, see Authentication in the Getting Started guide.

With NTLM (username + password)

{
  "mcpServers": {
    "devops-onprem": {
      "command": "uvx",
      "args": ["mcp-devops-onpremise@latest"],
      "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@latest"],
      "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

All configuration examples use mcp-devops-onpremise@latest, which instructs uvx to fetch the latest version automatically on every run.

For permanent installs and release notes, see Updating in the Getting Started guide.

Available Tools

Pull Requests

ToolDescriptionRead-only
devops_pull_request_getRetrieve a pull request by ID, including linked work items and commit SHAs for diffing✅
devops_pull_request_list_threadsReturns a hierarchical list of non-deleted comment threads and their text comments✅
devops_pull_request_list_thread_commentsList non-deleted text comments in a specific thread✅
devops_pull_request_create_commentCreate a new thread with an initial comment (general or inline on a file/line)❌
devops_pull_request_reply_commentReply to an existing comment thread❌
devops_pull_request_update_threadUpdate the status of a comment thread❌
devops_pull_request_update_commentUpdate the text of an existing comment❌
devops_pull_request_delete_commentDelete a comment from a pull request thread❌

Repositories

ToolDescriptionRead-only
devops_repository_listList all repositories in the project✅
devops_repository_getRetrieve repository details by name or ID✅
devops_repository_commit_changesList files changed in a specific commit✅
devops_repository_diffs_commitsGet the difference between two commits (changed file paths)✅
devops_repository_item_contentGet raw file content at a specific commit or branch✅
devops_get_item_content_diffGet line-level textual diff of a file between two commits (added lines prefixed +, removed -)✅

Work Items

ToolDescriptionRead-only
devops_work_item_getRetrieve 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_getDownload a work item attachment by its GUID, either saving locally or returning base64-encoded content✅
devops_work_item_type_getGet the definition of a work item type by name (e.g. Bug, User Story)✅
devops_work_item_query_by_wiqlExecute a WIQL (Work Item Query Language) query and return matching work items✅
devops_work_item_createCreate a new work item with typed fields; Html is the default format❌
devops_work_item_updateUpdate fields on a work item using JSON Patch (add / replace / remove)❌
devops_work_item_deleteDelete a work item, moves to Recycle Bin by default; use destroy=True for permanent deletion (requires project permission)❌
devops_work_item_undeleteRestore a soft-deleted work item from the Recycle Bin❌
devops_work_item_link_updateAdd or remove a relation link between two work items (parent, child, related, successor, predecessor, etc.)❌
devops_work_item_artifact_link_updateAdd or remove an artifact link (Pull Request, Build, Commit, Branch, Changeset) on a work item❌
devops_work_item_comment_listList comments on a work item with configurable page size and format✅
devops_work_item_comment_addAdd a comment to a work item❌
devops_work_item_comment_updateUpdate an existing comment on a work item❌
devops_work_item_comment_deleteDelete a comment from a work item❌

Wiki

ToolDescriptionRead-only
devops_wiki_page_get_by_urlGet wiki page metadata (id, path) and optional content by its URL✅
devops_wiki_page_create_or_updateCreate or update a wiki page under a specified parent page❌
devops_wiki_page_updateUpdate an existing wiki page by ID❌
devops_wiki_page_deleteDelete 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/
Ver o original no GitHub

Bom para

Relacionados