Azure DevOps Server (formerly TFS)
MCP server for on-premises Azure DevOps Server (TFS) with NTLM sign-in
- Pricing
- Open source
- Platforms
- CLI, self-hosted, Windows
- Runs
- Locally
- Version
- 2.2.0
- Listing updated
- 3 days ago
About Azure DevOps Server (formerly TFS)
Azure DevOps Server (formerly TFS) is an open-source MCP server for cloud and infrastructure. It runs locally on your machine and is started by your AI client.
The project exists because Microsoft's official Azure DevOps MCP server supports only the cloud service, Azure DevOps Services, and Microsoft has said it does not plan to support the on-premises Server edition. This one targets Azure DevOps Server, formerly Team Foundation Server, and says it is not for dev.azure.com.
Its main difference is NTLM authentication with Windows domain credentials, needed where the server only accepts NTLM or where VPN and domain access are required. Personal access tokens and OAuth bearer tokens work too. You supply the full project URL, such as https://server/org/project, through environment variables.
Assistants can browse repositories, review pull requests, manage work items and read or update wiki pages. It also retrieves commit diffs with added and removed lines, as the web UI shows them, to support code review. The maintainers say requested features are fast-tracked. It installs from PyPI with Python 3.10 or later and uv, and is released under Apache-2.0. The authors state it is a community project not affiliated with Microsoft.
Install
Run in a terminal
claude mcp add mcp-devops-on-prem --env DEVOPS_API_URL='<DEVOPS_API_URL>' --env DEVOPS_PASSWORD='<DEVOPS_PASSWORD>' --env DEVOPS_PAT='<DEVOPS_PAT>' --env DEVOPS_TOKEN='<DEVOPS_TOKEN>' -- uvx mcp-devops-onpremiseAdd to claude_desktop_config.json
{
"mcpServers": {
"mcp-devops-on-prem": {
"command": "uvx",
"args": [
"mcp-devops-onpremise"
],
"env": {
"DEVOPS_API_URL": "<DEVOPS_API_URL>",
"DEVOPS_PASSWORD": "<DEVOPS_PASSWORD>",
"DEVOPS_PAT": "<DEVOPS_PAT>",
"DEVOPS_TOKEN": "<DEVOPS_TOKEN>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp-devops-on-prem": {
"command": "uvx",
"args": [
"mcp-devops-onpremise"
],
"env": {
"DEVOPS_API_URL": "<DEVOPS_API_URL>",
"DEVOPS_PASSWORD": "<DEVOPS_PASSWORD>",
"DEVOPS_PAT": "<DEVOPS_PAT>",
"DEVOPS_TOKEN": "<DEVOPS_TOKEN>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp-devops-on-prem": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-devops-onpremise"
],
"env": {
"DEVOPS_API_URL": "<DEVOPS_API_URL>",
"DEVOPS_PASSWORD": "<DEVOPS_PASSWORD>",
"DEVOPS_PAT": "<DEVOPS_PAT>",
"DEVOPS_TOKEN": "<DEVOPS_TOKEN>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp-devops-on-prem": {
"command": "uvx",
"args": [
"mcp-devops-onpremise"
],
"env": {
"DEVOPS_API_URL": "<DEVOPS_API_URL>",
"DEVOPS_PASSWORD": "<DEVOPS_PASSWORD>",
"DEVOPS_PAT": "<DEVOPS_PAT>",
"DEVOPS_TOKEN": "<DEVOPS_TOKEN>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp-devops-on-prem": {
"command": "uvx",
"args": [
"mcp-devops-onpremise"
],
"env": {
"DEVOPS_API_URL": "<DEVOPS_API_URL>",
"DEVOPS_PASSWORD": "<DEVOPS_PASSWORD>",
"DEVOPS_PAT": "<DEVOPS_PAT>",
"DEVOPS_TOKEN": "<DEVOPS_TOKEN>"
}
}
}
}Configuration
DEVOPS_API_URLFull Azure DevOps Server project URL, e.g. https://server/org/projectRequiredDEVOPS_USERNAMENTLM username, usually DOMAIN\usernameDEVOPS_PASSWORDNTLM passwordDEVOPS_PATPersonal Access Token for PAT authenticationDEVOPS_TOKENOAuth bearer token for bearer-token authentication
What it does
- NTLM authentication
- Works with Windows domain credentials and VPN setups.
- PAT and bearer tokens
- Alternative authentication methods.
- Pull request review
- Read repositories, pull requests and comments.
- Work item management
- Create and update work items.
- Wiki access
- Read and update wiki pages.
- Commit diffs
- Added and removed lines like the web UI.
Good for
- Review a pull request on an on-prem server
- Create or update work items from chat
- Read project wiki pages for context
- Summarise a commit's changes
Pricing
Open source
Apache-2.0, free
Prices change. Check zwitbaum.github.io before you buy.
Azure DevOps Server (formerly TFS) FAQ
Does it work with Azure DevOps Services in the cloud?
No. It is for the on-premises Server edition only.
How do I authenticate?
NTLM with domain credentials, a personal access token or an OAuth bearer token.
What do I need installed?
Python 3.10 or later and uv.
Is it from Microsoft?
No, it is a community project not affiliated with or endorsed by Microsoft.
Is Azure DevOps Server (formerly TFS) free?
Yes. Azure DevOps Server (formerly TFS) is open source, so you can use and self-host it for free.
How do I add Azure DevOps Server (formerly TFS) to Claude Code?
Run this command in your terminal: claude mcp add mcp-devops-on-prem --env DEVOPS_API_URL='<DEVOPS_API_URL>' --env DEVOPS_PASSWORD='<DEVOPS_PASSWORD>' --env DEVOPS_PAT='<DEVOPS_PAT>' --env DEVOPS_TOKEN='<DEVOPS_TOKEN>' -- uvx mcp-devops-onpremise
What are the best alternatives to Azure DevOps Server (formerly TFS)?
The closest alternatives to Azure DevOps Server (formerly TFS) are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Azure DevOps Server (formerly TFS)

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools