Backlog MCP Server
Provides containerized deployment options for both development and production environments
Used for environment variable management, allowing configuration of Backlog API credentials through .env files
Referenced as a resource for setting up the Windsurf application with MCP capabilities
Click on "Deploy 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 Serversearch for open issues in PROJECT1"
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 Server
This is an MCP server that connects to Backlog's API. It provides the functionality to search, retrieve, and update issues.
function
Search for issues
Get an issue
Update an issue
Related MCP server: Backlog MCP Server
set up
MCP Configuration
Add the following to ~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json :
{
"mcpServers": {
"backlog": {
"command": "node",
"args": ["build/index.js"],
"cwd": "/path/to/backlog-mcp-server"
}
}
}Note: Replace cwd with the actual project path.
Docker environment
Development environment
If you use Docker containers for development and testing:
# .envファイルを作成
cp .env.example .env
# 必要な環境変数を設定
BACKLOG_SPACE_URL=https://your-space.backlog.com
BACKLOG_API_KEY=your_api_key
# 開発モードでビルドと起動
NODE_ENV=development docker compose up -d --buildIn development mode it will watch for changes in the source code and restart automatically.
Production
If you use Docker containers for production:
# .envファイルを作成
cp .env.example .env
# 必要な環境変数を設定
BACKLOG_SPACE_URL=https://your-space.backlog.com
BACKLOG_API_KEY=your_api_key
# 本番モードでビルドと起動
docker compose up -d --buildUse as an MCP server
To run an MCP server using a Docker container, set the following in the configuration file of the app you are using. Example for Cline and RooCline: cline_mcp_settings.json
{
"mcpServers": {
"backlog": {
"command": "docker",
"args": ["exec", "-i", "backlog-mcp-server", "node", "build/index.js"],
"env": {
"BACKLOG_SPACE_URL": "https://your-space.backlog.com",
"BACKLOG_API_KEY": "your_api_key"
}
}
}
}Other app settings methods
Claude Desktop: https://ainow.jp/claude-mcp-guide/
Windsurf: https://zenn.dev/y16ra/articles/3ed3e2ae734fa4
Cursor: https://note.com/shuzon\_\_/n/na2aafacf7324 →[Set Notion MCP Server as Cursor]
Example prompt
# 課題の検索
・バックログのPROJECT1-100の課題を説明して
・バックログのPROJECT1のプロジェクトで処理中の課題を教えて
# 課題の更新
・PROJECT1-100の課題のステータスを完了にして
・PROJECT1-100の課題に「〜〜〜」とコメントしてAvailable Tools
4 toolsgetIssueC
特定のBacklog課題を取得します
Inputs: issueId (required).
getProjectsB
Backlogのプロジェクト一覧を取得します
Inputs: no named parameters.
searchIssuesC
Backlogの課題を検索します
Inputs: projectId (required), keyword, status.
updateIssueC
Backlog課題を更新します
Inputs: issueId (required), status, description, comment.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: getIssue retrieves a specific issue, getProjects lists projects, searchIssues finds issues based on criteria, and updateIssue modifies an issue. There is no overlap or ambiguity between these functions.
The naming follows a consistent verb_noun pattern (e.g., getIssue, getProjects, searchIssues, updateIssue), with all tools using camelCase. The only minor deviation is that 'getProjects' uses a plural noun while others use singular, but this is still readable and predictable.
With only 4 tools, the set feels thin for a Backlog server, as it lacks essential operations like creating issues or projects, deleting resources, or managing comments. While the tools cover basic retrieval and update, the scope is incomplete for typical issue-tracking workflows.
There are significant gaps in the tool surface for a Backlog server. Missing operations include create_issue, delete_issue, create_project, and update_project, which are core to issue lifecycle management. This will likely cause agent failures when trying to perform full CRUD operations.
Related MCP Connectors
An MCP server that provides congressional transcripts
MCP server for searching Airweave collections with natural language queries.
An MCP server that integrates with Discord to provide AI-powered features.
A MCP server built for developers enabling Git based project management with project and personal…
Related MCP Servers
- AlicenseBqualityNot gradedmaintenanceAn MCP server implementation that integrates with Backlog API, enabling project management operations including issues, projects, and wikis through natural language interactions.1212,984 npm3-
- AlicenseBqualityDmaintenanceA read-only MCP server that enables users to retrieve and interact with Backlog projects, issues, pull requests, and notifications. It provides a secure way to query Backlog data through natural language using tools like Claude Desktop.102 npmMIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for integrating with Jira Server instances, enabling natural language interactions to create, update, search, and manage issues and comments.1,383 npm1MIT
- AlicenseAqualityDmaintenanceAn MCP server providing AI agents with read access to Backlog issues, comments, and attachments via API Key authentication.128 npmMIT