Azure DevOps MCP Server
The server lets AI assistants manage Azure DevOps resources (projects, repos, work items, PRs, pipelines, wikis) via MCP tools.
User & Organization: Get authenticated user info, list accessible organizations.
Projects: List, get, or fetch detailed project info (process, teams, work item types).
Repositories & Code: List/get repos, fetch file contents, browse repository trees, create branches, commit file changes (via unified diffs or search/replace), list commits.
Work Items: Create, update, retrieve, list, and link work items; add/remove attachments; get comments.
Search: Search code, wiki, and work items across projects.
Pull Requests: Create, view, update, list PRs; add/retrieve comments; get changes/checks; update thread status.
Pipelines: List/get pipelines, list runs, get run details, download artifacts, view timeline/logs, trigger runs with variables/parameters.
Wikis: List wikis, get/create/update pages, list pages.
Utilizes environment variables for configuration of organization URL, Personal Access Token, and default project settings.
Enables interaction with Git repositories in Azure DevOps, including accessing repository details and branch information.
Runs on Node.js to provide a server implementation for communicating with Azure DevOps resources via the Model Context Protocol.
Uses npm for package management and running scripts to build, test, and deploy the Azure DevOps MCP server.
Built using TypeScript, providing type-safe interaction with Azure DevOps APIs for projects, work items, repositories, pull requests, branches, and pipelines.
Supports yarn as an alternative package manager for installing dependencies and managing the project.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Azure DevOps MCP Server list open pull requests for the web-app repository"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Azure DevOps MCP Server
A Model Context Protocol (MCP) server implementation for Azure DevOps, allowing AI assistants to interact with Azure DevOps APIs through a standardized protocol.
Looking for the official server? Microsoft maintains a product-supported Azure DevOps MCP at microsoft/azure-devops-mcp. If you use Azure DevOps Services (cloud), start there.
This community server remains a good fit when you need Azure DevOps Server (on-premises) support — especially older versions that may not work with Microsoft's MCP — or features not yet available in the official server. See Discussion #237 for more context. See ROADMAP.md for where this server differentiates and what is planned.
Overview
This server implements the Model Context Protocol (MCP) for Azure DevOps, enabling AI assistants like Claude to interact with Azure DevOps resources securely. The server acts as a bridge between AI models and Azure DevOps APIs, providing a standardized way to:
Access and manage projects, work items, repositories, and more
Create and update work items, branches, and pull requests
Execute common DevOps workflows through natural language
Access repository content via standardized resource URIs
Safely authenticate and interact with Azure DevOps resources
Related MCP server: Azure DevOps MCP Server
Server Structure
The server is structured around the Model Context Protocol (MCP) for communicating with AI assistants. It provides tools for interacting with Azure DevOps resources including:
Projects
Work Items
Repositories
Pull Requests
Branches
Pipelines
Core Components
AzureDevOpsServer: Main server class that initializes the MCP server and registers tools
Feature Modules: Organized by feature area (work-items, projects, repositories, etc.)
Request Handlers: Each feature module provides request identification and handling functions
Tool Handlers: Modular functions for each Azure DevOps operation
Configuration: Environment-based configuration for organization URL, PAT, etc.
The server uses a feature-based architecture where each feature area (like work-items, projects, repositories) is encapsulated in its own module. This makes the codebase more maintainable and easier to extend with new features.
Getting Started
Prerequisites
Node.js (v16+)
npm or yarn
Azure DevOps account with appropriate access
Authentication credentials (see Authentication Guide for details):
Personal Access Token (PAT), or
Azure Identity credentials, or
Azure CLI login
Running from npm (npx)
If you just want to run the published server package, you do not need to clone or build this repository:
npx -y @tiberriver256/mcp-server-azure-devopsRunning locally (from source)
From a checkout of this repository:
npm ci
cp .env.example .env # then edit values
npm run build
npm start # runs: node dist/index.jsFor iterative development (auto-reload):
npm run dev # runs src/index.ts via tsx watchUsage with Claude Desktop/Cursor AI
To integrate with Claude Desktop or Cursor AI, add one of the following configurations to your configuration file.
Azure Identity Authentication
Be sure you are logged in to Azure CLI with az login then add the following:
{
"mcpServers": {
"azureDevOps": {
"command": "npx",
"args": ["-y", "@tiberriver256/mcp-server-azure-devops"],
"env": {
"AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/your-organization",
"AZURE_DEVOPS_AUTH_METHOD": "azure-identity",
"AZURE_DEVOPS_DEFAULT_PROJECT": "your-project-name"
}
}
}
}Personal Access Token (PAT) Authentication
{
"mcpServers": {
"azureDevOps": {
"command": "npx",
"args": ["-y", "@tiberriver256/mcp-server-azure-devops"],
"env": {
"AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/your-organization",
"AZURE_DEVOPS_AUTH_METHOD": "pat",
"AZURE_DEVOPS_PAT": "<YOUR_PAT>",
"AZURE_DEVOPS_DEFAULT_PROJECT": "your-project-name"
}
}
}
}Azure DevOps Server (on-prem) requires PAT authentication. Example:
{
"mcpServers": {
"azureDevOps": {
"command": "npx",
"args": ["-y", "@tiberriver256/mcp-server-azure-devops"],
"env": {
"AZURE_DEVOPS_ORG_URL": "https://server:8080/tfs/DefaultCollection",
"AZURE_DEVOPS_AUTH_METHOD": "pat",
"AZURE_DEVOPS_PAT": "<YOUR_PAT>",
"AZURE_DEVOPS_DEFAULT_PROJECT": "your-project-name"
}
}
}
}For detailed configuration instructions and more authentication options, see the Authentication Guide.
Authentication Methods
This server supports multiple authentication methods for connecting to Azure DevOps APIs. For detailed setup instructions, configuration examples, and troubleshooting tips, see the Authentication Guide.
Supported Authentication Methods
Personal Access Token (PAT) - Simple token-based authentication
Azure Identity (DefaultAzureCredential) - Flexible authentication using the Azure Identity SDK
Azure CLI - Authentication using your Azure CLI login
Example configuration files for each authentication method are available in the examples directory.
Azure DevOps Server (on-prem) supports PAT authentication only. Azure Identity and Azure CLI are supported for Azure DevOps Services.
Environment Variables
For a complete list of environment variables and their descriptions, see the Authentication Guide.
Key environment variables include:
Variable | Description | Required | Default |
| Authentication method ( | No |
|
| Full URL to your Azure DevOps organization or Server collection (e.g., | Yes | - |
| Personal Access Token (for PAT auth) | Only with PAT auth | - |
| Default project if none specified | No | - |
| REST api-version for the tools that call the REST API directly (per-release values) | No |
|
| Azure AD tenant ID (for service principals) | Only with service principals | - |
| Azure AD application ID (for service principals) | Only with service principals | - |
| Azure AD client secret (for service principals) | Only with service principals | - |
| Logging level (debug, info, warn, error) | No | info |
Troubleshooting Authentication
For detailed troubleshooting information for each authentication method, see the Authentication Guide.
Common issues include:
Invalid or expired credentials
Insufficient permissions
Network connectivity problems
Configuration errors
Authentication Implementation Details
For technical details about how authentication is implemented in the Azure DevOps MCP server, see the Authentication Guide and the source code in the src/auth directory.
Available Tools
The Azure DevOps MCP server provides a variety of tools for interacting with Azure DevOps resources. For detailed documentation on each tool, please refer to the corresponding documentation.
User Tools
get_me: Get details of the authenticated user (id, displayName, email) (Azure DevOps Services only)
Organization Tools
list_organizations: List all accessible organizations (Azure DevOps Services only)
Project Tools
list_projects: List all projects in an organizationget_project: Get details of a specific projectget_project_details: Get comprehensive details of a project including process, work item types, and teams
Repository Tools
list_repositories: List all repositories in a projectget_repository: Get details of a specific repositoryget_repository_details: Get detailed information about a repository including statistics and refsget_file_content: Get content of a file or directory from a repositoryget_repository_tree: List a repository's file tree from any path and depthcreate_branch: Create a new branch from an existing onecreate_commit: Commit multiple file changes to a branch using unified diffs or search/replace instructions
Work Item Tools
get_work_item: Retrieve a work item by IDcreate_work_item: Create a new work itemupdate_work_item: Update an existing work itemlist_work_items: List work items in a projectmanage_work_item_link: Add, remove, or update links between work itemscreate_work_item_attachment: Upload and attach a file to a work itemget_work_item_attachment: Download an attachment from a work itemdelete_work_item_attachment: Delete an attachment from a work item
Search Tools
search_code: Search for code across repositories in a projectsearch_wiki: Search for content across wiki pages in a projectsearch_work_items: Search for work items across projects in Azure DevOps
Pipelines Tools
list_pipelines: List pipelines in a projectget_pipeline: Get details of a specific pipelinelist_pipeline_runs: List recent runs for a pipeline with optional filtersget_pipeline_run: Get detailed run information and artifact summariesdownload_pipeline_artifact: Download a single artifact file as textpipeline_timeline: Retrieve the stage and job timeline for a runget_pipeline_log: Retrieve raw or JSON-formatted log contenttrigger_pipeline: Trigger a pipeline run with customizable parameters
Wiki Tools
get_wikis: List all wikis in a projectget_wiki_page: Get content of a specific wiki page as plain text
Pull Request Tools
create_pull_request- Create a new pull requestget_pull_request- Get a pull request by IDlist_pull_requests- List pull requests in a repositoryadd_pull_request_comment- Add a comment to a pull requestget_pull_request_comments- Get comments from a pull requestupdate_pull_request- Update an existing pull request (title, description, status, draft state, reviewers, work items)get_pull_request_changes- List changes in a pull request and policy evaluation statusget_pull_request_checks- Summarize status checks, policy evaluations, and their related pipelines
For comprehensive documentation on all tools, see the Tools Documentation.
Contributing
Contributions are welcome! Please see CONTRIBUTING.md for contribution guidelines.
Star History
License
MIT
Available Tools
49 toolsadd_pull_request_commentB
Add a comment to a pull request (repositoryId optional; derived from pullRequestId when omitted)
Inputs: content (required), pullRequestId (required), status, filePath, +6 more.
create_branchB
Create a new branch from an existing one
Inputs: newBranch (required), repositoryId (required), sourceBranch (required), projectId, +1 more.
create_commitA
Create a commit on an existing branch using file changes.
Provide plain branch names (no "refs/heads/").
⚠️ Each file path may appear only once per commit request—combine all edits to a file into a single change entry.
Prefer multiple commits when you have sparse or unrelated edits; smaller focused commits keep review context clear.
🎯 RECOMMENDED: Use the SEARCH/REPLACE format (much easier, no line counting!).
Option 1: SEARCH/REPLACE format (EASIEST) Simply provide the exact text to find and replace:
{
"changes": [{
"path": "src/api/services/function-call.ts",
"search": "return axios.post(apiUrl, payload, requestConfig);",
"replace": "return axios.post(apiUrl, payload, requestConfig).then(r => { processResponse(r); return r; });"
}]
}The server fetches the file, performs the replacement, and generates the diff automatically. No line counting, no hunk headers, no context lines needed!
Option 2: UNIFIED DIFF format (Advanced) If you prefer full control, provide complete unified diffs:
Each patch MUST have complete hunk headers: @@ -oldStart,oldLines +newStart,newLines @@
CRITICAL: Every @@ marker MUST include line numbers. Do NOT use @@ without line ranges.
Include 3-5 context lines before and after changes.
For deletions:
--- a/filepathand+++ /dev/nullFor additions:
--- /dev/nulland+++ b/filepath
Example unified diff:
{
"changes": [{
"patch": "diff --git a/file.yaml b/file.yaml\n--- a/file.yaml\n+++ b/file.yaml\n@@ -4,7 +4,7 @@ spec:\n spec:\n type: ClusterIP\n ports:\n- - port: 8080\n+ - port: 9090\n targetPort: http\n"
}]
}Inputs: changes (required), branchName (required), repositoryId (required), commitMessage (required), +2 more.
create_pull_requestB
Create a new pull request, including reviewers, linked work items, and optional tags
Inputs: title (required), repositoryId (required), sourceRefName (required), targetRefName (required), +8 more.
create_wikiC
Create a new wiki in the project
Inputs: name (required), type (required), mappedPath (required), projectId, +2 more.
create_wiki_pageA
Create a new page in a wiki. If the page already exists at the specified path, it will be updated.
Inputs: wikiId (required), content (required), pagePath (required), comment, +2 more.
create_work_itemC
Create a new work item
Inputs: title (required), workItemType (required), tags, areaPath, +8 more.
create_work_item_attachmentA
Upload a file and attach it to a work item. The file is read from the local filesystem, uploaded to Azure DevOps, and linked to the specified work item.
Inputs: filePath (required), workItemId (required), comment, fileName.
delete_work_item_attachmentA
Delete an attachment from a work item. The attachment ID can be obtained from the work item relations.
Inputs: workItemId (required), attachmentId (required).
download_pipeline_artifactB
Download a file from a pipeline run artifact and return its textual content
Inputs: runId (required), artifactPath (required), projectId, pipelineId.
get_all_repositories_treeB
Displays a hierarchical tree view of files and directories across multiple Azure DevOps repositories within a project, based on their default branches
Inputs: depth (required), pattern, projectId, organizationId, +1 more.
get_file_contentC
Get content of a file or directory from a repository
Inputs: path (required), repositoryId (required), version, projectId, +2 more.
get_meA
Get details of the authenticated user (id, displayName, email)
Inputs: no named parameters.
get_pipelineC
Get details of a specific pipeline
Inputs: pipelineId (required), projectId, pipelineVersion.
get_pipeline_logC
Retrieve a specific pipeline log using the timeline log identifier
Inputs: logId (required), runId (required), format, endLine, +3 more.
get_pipeline_runC
Get details for a specific pipeline run
Inputs: runId (required), projectId, pipelineId.
get_projectC
Get details of a specific project
Inputs: projectId, organizationId.
get_project_detailsC
Get comprehensive details of a project including process, work item types, and teams
Inputs: includeTeams (required), includeFields (required), includeProcess (required), expandTeamIdentity (required), +3 more.
get_pull_requestA
Get a pull request by ID (no repositoryId required; best for Azure DevOps Server where PR IDs are project-scoped)
Inputs: projectId (required), pullRequestId (required), organizationId.
get_pull_request_changesA
Get the files changed in a pull request, their unified diffs, source/target branch names, and the status of policy evaluations
Inputs: repositoryId (required), pullRequestId (required), projectId, organizationId.
get_pull_request_checksA
Summarize the latest status checks and policy evaluations for a pull request.
Surfaces pipeline and run identifiers so you can jump straight to the blocking validation.
Pair with pipeline tools (e.g., get_pipeline_run, pipeline_timeline) to inspect failures in depth.
Inputs: repositoryId (required), pullRequestId (required), projectId, organizationId.
get_pull_request_commentsC
Get comments from a specific pull request
Inputs: repositoryId (required), pullRequestId (required), top, threadId, +3 more.
get_repositoryB
Get details of a specific repository
Inputs: repositoryId (required), projectId, organizationId.
get_repository_detailsC
Get detailed information about a repository including statistics and refs
Inputs: includeRefs (required), repositoryId (required), includeStatistics (required), projectId, +3 more.
get_repository_treeB
Displays a hierarchical tree view of files and directories within a single repository starting from an optional path
Inputs: path (required), depth (required), repositoryId (required), projectId, +1 more.
get_wiki_pageB
Get the content of a wiki page
Inputs: wikiId (required), pagePath (required), projectId, organizationId.
get_wikisC
Get details of wikis in a project
Inputs: projectId, organizationId.
get_work_itemC
Get details of a specific work item
Inputs: workItemId (required), expand.
get_work_item_attachmentB
Download an attachment from Azure DevOps and save it to the local filesystem. The attachment ID can be obtained from the work item relations.
Inputs: outputPath (required), attachmentId (required).
get_work_item_commentsC
Get comments and discussion history for a specific work item
Inputs: order (required), expand (required), workItemId (required), top, +3 more.
list_commitsB
List recent commits on a branch including file-level diff content for each commit
Inputs: branchName (required), repositoryId (required), top, skip, +2 more.
list_organizationsA
List all Azure DevOps organizations accessible to the current authentication
Inputs: no named parameters.
list_pipeline_runsC
List recent runs for a pipeline
Inputs: top (required), orderBy (required), pipelineId (required), state, +6 more.
list_pipelinesB
List pipelines in a project
Inputs: top, orderBy, projectId.
list_projectsC
List all projects in an organization
Inputs: top, skip, stateFilter, organizationId, +1 more.
list_pull_requestsC
List pull requests in a repository
Inputs: top (required), repositoryId (required), skip, status, +6 more.
list_repositoriesC
List repositories in a project
Inputs: projectId, includeLinks, organizationId.
list_wiki_pagesC
List pages within an Azure DevOps wiki
Inputs: wikiId (required), projectId, organizationId.
list_work_itemsC
List work items in a project
Inputs: top, skip, wiql, fields, +4 more.
manage_work_item_linkC
Add or remove links between work items
Inputs: operation (required), relationType (required), sourceWorkItemId (required), targetWorkItemId (required), +4 more.
pipeline_timelineC
Retrieve the timeline of stages and jobs for a pipeline run, to reduce the amount of data returned, you can filter by state and result
Inputs: runId (required), state, result, projectId, +2 more.
search_codeC
Search for code across repositories in a project
Inputs: top (required), skip (required), searchText (required), includeContent (required), +4 more.
search_wikiC
Search for content across wiki pages in a project
Inputs: top (required), skip (required), searchText (required), includeFacets (required), +3 more.
search_work_itemsC
Search for work items across projects in Azure DevOps
Inputs: top (required), skip (required), searchText (required), includeFacets (required), +4 more.
trigger_pipelineC
Trigger a pipeline run
Inputs: pipelineId (required), branch, projectId, variables, +2 more.
update_pull_requestB
Update an existing pull request with new properties, manage reviewers and work items, and add or remove tags
Inputs: repositoryId (required), pullRequestId (required), title, status, +11 more.
update_pull_request_thread_statusA
Update the status of a comment thread in a pull request (repositoryId optional; derived from pullRequestId when omitted)
Inputs: status (required), threadId (required), pullRequestId (required), projectId, +2 more.
update_wiki_pageC
Update content of a wiki page
Inputs: wikiId (required), content (required), pagePath (required), comment, +2 more.
update_work_itemC
Update an existing work item
Inputs: workItemId (required), tags, state, title, +8 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 49 tools
Many tools are distinct by resource and action (repositories, work items, PRs, wikis, pipelines), but several overlapping pairs create ambiguity: get_project_details vs get_project, get_repository_details vs get_repository, get_file_content vs tree tools, and create_wiki_page (which also updates) vs update_wiki_page. Descriptions help clarify, but the boundaries are not consistently sharp.
Most tools follow a predictable snake_case verb_noun pattern (list_repositories, get_work_item, create_pull_request, update_wiki_page). Minor deviations exist, such as pipeline_timeline lacking a verb and get_wikis vs list_wiki_pages, but the overall convention is readable and mostly consistent.
49 tools is excessive for a single MCP server, far beyond the 3-15 well-scoped range and even beyond the 16-25 heavy range. Azure DevOps is broad, but this surface would benefit from consolidation or grouping.
The server covers many core read/write operations across repositories, work items, PRs, wikis, and pipelines. However, notable lifecycle gaps remain: no delete_work_item, no PR merge/abandon/complete operation, no repository create/delete, no wiki page delete, and no pipeline cancel/update.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents.
A Model Context Protocol server for Wix AI tools
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceThis server provides a convenient API for interacting with Azure DevOps services, enabling AI assistants and other tools to manage work items, code repositories, boards, sprints, and more. Built with the Model Context Protocol, it provides a standardized interface for communicating with Azure DevOps164 npm60MIT
- -licenseNot gradedqualityNot gradedmaintenanceA reference server implementation for the Model Context Protocol that enables AI assistants to interact with Azure DevOps resources and perform operations such as project management, work item tracking, repository operations, and code search programmatically.7-
- AlicenseAqualityDmaintenanceA Model Context Protocol server that enables AI assistants to interact with Azure DevOps services, allowing users to query work items with plans to support creating/updating items, managing pipelines, handling pull requests, and administering sprints and branch policies.2155 PyPI79MIT
- FlicenseAqualityDmaintenanceA Model Context Protocol server that enables AI assistants to interact with Azure DevOps services, providing capabilities for work item management, project management, and team collaboration through natural language.21-