Click on "Install 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., "@Backlog MCP Serverlist all open tasks"
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.
backlog-mcp
Minimal task backlog MCP server for Claude and AI agents.
Quick start: Tell your LLM:
Add backlog-mcp to .mcp.json and use it to track tasks
Web Viewer
Start the server and open http://localhost:3030 for a visual task browser.
Features:
Split pane layout with task list and detail view
Filter by Active/Completed/All
GitHub-style markdown rendering
Click file path to open in editor
URL state persistence
Task Schema
Tasks are stored as individual markdown files with YAML frontmatter:
Status values: open, in_progress, blocked, done, cancelled
MCP Tool
Single unified tool with action parameter:
Installation
Add to your MCP config (.mcp.json or Claude Desktop config):
Or build from source:
Storage
Default:
data/tasks/anddata/archive/(local to project)Global: Set
BACKLOG_DATA_DIR=~/.backlogfor cross-project persistenceCompleted/cancelled tasks auto-archive to
archive/
License
MIT