This MCP (Model Context Protocol) server provides tools for interacting with Azure DevOps services through AI assistants.
Architecture
The server follows an entity-based architecture that groups operations by resource type rather than exposing many atomic tools. This approach provides several benefits:
Intuitive organization: Tools are organized by the entities they operate on (projects, repositories, work items, etc.)
Azure DevOps MCP Server
星數
17
工具
—
可用率
—
Reduced tool count: Instead of dozens of individual tools, we have a handful of entity tools with multiple operations
Consistent interface: All entity tools follow the same pattern for operations and parameters
Better error handling: Each entity tool can handle errors specific to its domain
Easier discovery: Users can easily discover available operations for each entity
Entity Tools: Each tool represents a major Azure DevOps entity (projects, repositories, work items, etc.) and provides multiple operations (list, get, create, etc.)
Tool Registry: Manages the registration and execution of entity tools
API Client: Handles communication with the Azure DevOps REST API
Error Utilities: Provides standardized error handling with detailed context and user-friendly messages
Pagination Utilities: Implements cursor-based pagination for list operations
Configuration Manager: Loads and validates configuration from environment variables or config file
Recent Improvements
1. Enhanced Error Handling
The server now includes a comprehensive error handling system that provides:
Categorized errors: Errors are categorized by type (authentication, authorization, validation, etc.)
Contextual information: Errors include the source, operation, and other relevant context
User-friendly messages: Error messages are designed to be helpful and actionable
Troubleshooting tips: Where applicable, errors include suggestions for resolving the issue
flowchart LR
Error[API Error] --> Handler[Error Handler]
Handler --> Category{Categorize}
Category -->|Authentication| AuthError[Authentication Error]
Category -->|Authorization| AuthzError[Authorization Error]
Category -->|Not Found| NotFoundError[Not Found Error]
Category -->|Validation| ValidationError[Validation Error]
Category -->|Rate Limit| RateLimitError[Rate Limit Error]
Category -->|Service| ServiceError[Service Error]
Category -->|Unknown| UnknownError[Unknown Error]
AuthError & AuthzError & NotFoundError & ValidationError & RateLimitError & ServiceError & UnknownError --> Format[Format User Message]
Format --> McpError[MCP Error Response]
classDef error fill:#EA4335,stroke:#980905,color:white
classDef process fill:#4285F4,stroke:#0D47A1,color:white
classDef result fill:#34A853,stroke:#0D652D,color:white
class Error,AuthError,AuthzError,NotFoundError,ValidationError,RateLimitError,ServiceError,UnknownError error
class Handler,Category,Format process
class McpError result
2. Cursor-based Pagination
All list operations now support cursor-based pagination with:
Continuation tokens: Encoded tokens for resuming pagination
Customizable page size: Control the number of results per page
Consistent interface: Same pagination parameters across all list operations
Efficient resource usage: Only fetch the data you need
sequenceDiagram
participant Client as AI Assistant
participant Server as MCP Server
participant API as Azure DevOps API
Client->>Server: List request (maxResults=10)
Server->>API: API request (top=10, skip=0)
API->>Server: Response with items
Note over Server: Create continuation token
Server->>Client: Response with items and token
Client->>Server: List request with token
Note over Server: Decode token to get position
Server->>API: API request (top=10, skip=10)
API->>Server: Response with more items
Server->>Client: Response with items and new token
3. Improved Documentation
Each tool and operation now includes:
Detailed descriptions: Clear explanations of what each tool and operation does
Parameter documentation: Comprehensive documentation for all parameters
Usage examples: Real-world examples of how to use each operation
Type information: Clear type definitions for all inputs and outputs
Available Entity Tools
Projects Tool
Manages Azure DevOps projects.
Operations:
list: List all projects in the organization with pagination support
get: Get detailed information about a specific project
Repositories Tool
Manages Git repositories.
Operations:
list: List all Git repositories in a project with pagination support
get: Get detailed information about a specific Git repository
listBranches: List all branches in a Git repository with pagination support
Work Items Tool
Manages work items (bugs, tasks, user stories, etc.).
Operations:
get: Get detailed information about a specific work item
create: Create a new work item in a project
Pull Requests Tool
Manages pull requests in repositories.
Operations:
list: List pull requests in a repository with filtering and pagination support
get: Get detailed information about a specific pull request
Pipelines Tool
Manages CI/CD pipelines.
Operations:
list: List all pipelines in a project with pagination support
get: Get detailed information about a specific pipeline