Backlog MCP server

The MCP Backlog Server enables seamless integration between Backlog project management and Claude through the Model Context Protocol (MCP). This server provides structured access to Backlog projects, issues, and wikis directly within Claude, allowing for powerful data retrieval and analysis capabilities.

Installation

Prerequisites

To use the MCP Backlog Server, you'll need:

• An active Backlog account with API access
• Claude Desktop installed on your computer

Setup Steps

1. Download or clone the MCP Backlog Server repository

2. Install dependencies:

   npm install
   

3. Build the server:

   npm run build
   

4. Add server configuration to Claude Desktop:

   For MacOS: Edit ~/Library/Application Support/Claude/claude_desktop_config.json

   For Windows: Edit %APPDATA%/Claude/claude_desktop_config.json

   Add the following configuration:

   {
     "mcpServers": {
       "mcp-backlog-server": {
         "command": "/path/to/mcp-backlog-server/build/index.js",
         "env": {
           "BACKLOG_API_KEY": "your-api-key",
           "BACKLOG_SPACE_URL": "https://your-space.backlog.com"
         }
       }
     }
   }
   

   Make sure to:

   • Replace /path/to/mcp-backlog-server with the actual path to the server directory
   • Add your Backlog API key in the BACKLOG_API_KEY field
   • Set your Backlog space URL in the BACKLOG_SPACE_URL field (e.g., https://your-space.backlog.com)

5. Restart Claude Desktop to apply the changes

Troubleshooting Installation

If you encounter issues with the server connection, you can use the MCP Inspector for debugging:

npm run inspector

This will provide a URL to access debugging tools in your browser.

Using the MCP Backlog Server

Once installed, you can access Backlog through Claude using various resource URIs and tools.

Accessing Resources

You can reference Backlog projects using the URI format:

• backlog://project/[id] - Access a specific Backlog project

Available Tools

User and Space Information

• get_backlog_user - Get information about the current Backlog user
• get_backlog_space - Get information about the Backlog space

Projects

• list_recent_projects - List recently viewed Backlog projects

  Options:
  - count: Number of projects to retrieve
  - order: Sort order for results
  

Issues

• get_project_issues - Get issues for a specific project

  Options:
  - projectId: ID of the project
  - statusId: Filter by status
  - assigneeId: Filter by assignee
  - count: Number of issues to retrieve
  - offset: Pagination offset
  

• get_issue_detail - Get detailed information about a specific issue

• get_issue_comments - Get comments on an issue

• add_issue_comment - Add a comment to an issue

• get_issue_comment_count - Get the comment count for an issue

• get_issue_comment - Get a specific comment

Wiki Pages

• get_wiki_page_list - Get a list of wiki pages

  Options:
  - projectIdOrKey: Project identifier
  - keyword: Search term for filtering
  

• get_wiki_page - Get a specific wiki page

• update_wiki_page - Update a wiki page

Analysis Prompts

The server provides several analysis capabilities:

• summarize_projects - Generate summaries of recently viewed Backlog projects
• analyze_backlog_usage - Analyze Backlog usage patterns based on user, space, and project data
• summarize_wiki_pages - Generate summaries of wiki pages within a project

Example Usage

To list your recent projects in Claude:

1. Ask Claude to use the tool: "Please list my recent Backlog projects"
2. Claude will execute the list_recent_projects tool and return the results

To analyze project issues:

1. Ask Claude: "Show me all open issues in my Backlog project XYZ and summarize them"
2. Claude will use the appropriate tools to fetch and analyze the requested data

To update wiki pages:

1. Ask Claude: "Update the wiki page 'Project Overview' with this new content..."
2. Claude will use the update_wiki_page tool to make the requested changes

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.