Overview
What is Backlog MCP Server?
A Model Context Protocol (MCP) server that provides tools for managing projects, issues, wiki pages, and more through the Backlog API, enabling Claude users to interact with their Backlog account directly.
How to use Backlog MCP Server?
Install via npx by adding the server configuration to Claude’s MCP settings, setting the BACKLOG_DOMAIN and BACKLOG_API_KEY environment variables. Alternatively, clone the repository, install dependencies (npm install), build (npm run build), create a .env file with the same variables, and start the server (npm start).
Key features of Backlog MCP Server
- Project management – create, read, update, delete projects
- Issue tracking – create, update, delete, list issues
- Wiki page management – list, and more wiki operations
- Easy integration with Claude via npx
- Manual installation and customization supported
Use cases of Backlog MCP Server
- List all Backlog projects directly in a Claude conversation
- Create a new bug issue with priority and title in a specific project
- Retrieve and review the details of a given Backlog project
- Manage Backlog data without leaving the Claude interface
FAQ from Backlog MCP Server
What are the prerequisites for using Backlog MCP Server?
You need Node.js v16 or higher, a Backlog account with API access, and your Backlog API key.
How do I configure my Backlog API key?
Set the environment variables BACKLOG_DOMAIN (e.g., your-domain.backlog.com) and BACKLOG_API_KEY in the MCP configuration or in a .env file.
What tools are available in the server?
The server includes tools like get_project_list, add_issue, add_project, get_project, update_project, delete_project, and get_wiki_pages.
Can I install the server manually instead of using npx?
Yes – clone the repository, run npm install, build with npm run build, create a .env file, and start with npm start.
Is there a way to test the server?
Run npm test to execute the included tests.