VersionOne MCP Server
Enables AI assistants to query VersionOne for stories, features (epics), and their details with structured output.
README
VersionOne MCP Server
A simplified Model Context Protocol (MCP) server using FastMCP for VersionOne API integration. This server enables AI assistants to query VersionOne for stories, features (epics), and their details with structured output.
Features
The server provides four main tools with structured Pydantic models:
- get_stories - Get a list of stories from VersionOne
- get_story_details - Get detailed information about a specific story by ID
- get_features - Get a list of features (Epics) from VersionOne
- get_feature_details - Get detailed information about a specific feature by ID
Prerequisites
- Python 3.10 or higher
- uv package manager
- VersionOne access token
- Your VersionOne instance URL
Installation
- Install uv (if not already installed):
curl -LsSf https://astral.sh/uv/install.sh | sh
- Clone or download this project:
cd versionone-mcp-server
- Install dependencies with uv:
uv sync
- Configure your VersionOne credentials:
cp env-template.txt .env
- Edit
.envwith your actual VersionOne details:
# Your VersionOne base URL (e.g., https://www7.v1host.com/V1Instance)
VERSIONONE_BASE_URL=https://your-v1-host.com/YourInstance
# Your VersionOne access token (recommended)
VERSIONONE_ACCESS_TOKEN=your-access-token-here
Getting Your VersionOne Access Token
- Log into your VersionOne instance
- Navigate to your profile settings
- Go to the Applications page
- Create a new access token
- Copy the token to your
.envfile
Configuration
Environment Variables
VERSIONONE_BASE_URL: Your VersionOne instance URL (e.g.,https://www7.v1host.com/V1Instance)VERSIONONE_ACCESS_TOKEN: Your VersionOne access token (recommended method)
MCP Configuration
Add this server to your MCP client configuration:
{
"mcpServers": {
"versionone": {
"command": "uv",
"args": ["run", "server", "stdio"],
"cwd": "/path/to/versionone-mcp-server",
"env": {
"VERSIONONE_BASE_URL": "https://your-v1-host.com/YourInstance",
"VERSIONONE_ACCESS_TOKEN": "your-access-token-here"
}
}
}
}
Usage
Running the Server
uv run server stdio
Available Tools
1. get_stories
Get a list of stories from VersionOne with optional filtering.
Parameters:
filters(optional): Object containing query filterswhere: Where clause for filtering (e.g.,'AssetState!="Dead"')sel: Comma-separated list of attributes to select (e.g.,'Name,Number,Description')sort: Sort order (e.g.,'Name')
page_size(optional): Number of items per page (default: 20)page_start(optional): Starting page number (default: 0)
Example:
{
"name": "get_stories",
"arguments": {
"filters": {
"where": "AssetState!=\"Dead\"",
"sel": "Name,Number,Description,Status"
},
"page_size": 10
}
}
2. get_story_details
Get detailed information about a specific story by ID.
Parameters:
story_id(required): The ID of the story (e.g.,"Story:1234")attributes(optional): List of specific attributes to retrieve
Example:
{
"name": "get_story_details",
"arguments": {
"story_id": "Story:1234",
"attributes": ["Name", "Description", "Status", "Owner"]
}
}
3. get_features
Get a list of features (Epics) from VersionOne with optional filtering.
Parameters:
filters(optional): Object containing query filterswhere: Where clause for filteringsel: Comma-separated list of attributes to selectsort: Sort order
page_size(optional): Number of items per page (default: 20)page_start(optional): Starting page number (default: 0)
Example:
{
"name": "get_features",
"arguments": {
"filters": {
"where": "AssetState!=\"Dead\"",
"sel": "Name,Number,Description,Status"
}
}
}
4. get_feature_details
Get detailed information about a specific feature by ID.
Parameters:
feature_id(required): The ID of the feature/epic (e.g.,"Epic:1234")attributes(optional): List of specific attributes to retrieve
Example:
{
"name": "get_feature_details",
"arguments": {
"feature_id": "Epic:1234",
"attributes": ["Name", "Description", "Status", "Owner"]
}
}
VersionOne API Reference
This MCP server is built on top of the VersionOne REST API. For more detailed information about:
- Asset types and their relationships
- Available attributes for filtering and selection
- Query syntax and filtering options
- Authentication methods
Please refer to the official VersionOne API documentation at: https://versionone.github.io/api-docs/
Common Asset Types
- Story: User stories and backlog items
- Epic: Features and large work items
- Defect: Bugs and issues
- Task: Development tasks
- Test: Test cases
- Scope: Projects
- Timebox: Sprints/Iterations
Common Attributes
Name: The title/name of the itemNumber: The auto-generated number (e.g., S-1001)Description: Detailed descriptionStatus: Current status of the itemOwner: Assigned team memberAssetState: State of the asset (Active, Closed, etc.)CreateDate: When the item was createdChangeDate: When the item was last modified
Error Handling
The server includes comprehensive error handling for:
- Network connectivity issues
- Authentication failures
- Invalid API requests
- Missing or malformed parameters
Errors are logged and returned in a user-friendly format.
Development
Running in Development Mode
# Install development dependencies
uv sync --dev
# Run with debug logging
uv run server stdio
Testing
You can test the server using any MCP-compatible client or by running individual functions with the VersionOne API directly.
Security
- Always use access tokens instead of username/password when possible
- Keep your access tokens secure and rotate them regularly
- Use environment variables for sensitive configuration
- Never commit credentials to version control
Troubleshooting
Common Issues
-
"VersionOne client not initialized"
- Check that your environment variables are set correctly
- Verify your VersionOne URL format
- Ensure your access token is valid
-
Authentication errors (401)
- Verify your access token is correct and not expired
- Check that your VersionOne URL is correct
- Try creating a new access token
-
Network timeouts
- Check your internet connection
- Verify the VersionOne server is accessible
- Try increasing the timeout in the code if needed
Debugging
Enable debug logging by setting the log level in the server code:
logging.basicConfig(level=logging.DEBUG)
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
This project is provided as-is for educational and development purposes.
Support
For issues related to:
- This MCP server: Create an issue in this repository
- VersionOne API: Refer to VersionOne documentation or support
- MCP protocol: Refer to the MCP specification documentation
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.