Backlog MCP Server

@MCP-Mirror

代码仓库

基本信息

分类

其他

许可证

MIT license

传输方式

stdio

作者

MCP-Mirror

关于 Backlog MCP Server

Mirror of

#backlog #mcp-server #project-management

Backlog MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "backlog": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "BACKLOG_DOMAIN",
        "-e",
        "BACKLOG_API_KEY",
        "ghcr.io/nulab/backlog-mcp-server"
      ],
      "env": {
        "BACKLOG_DOMAIN": "your-domain.backlog.com",
        "BACKLOG_API_KEY": "your-api-key"
      }
    }
  }
}

Backlog MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Backlog MCP Server?

A Model Context Protocol (MCP) server that enables AI agents like Claude Desktop, Cline, and Cursor to interact with the Backlog API. It provides tools for managing projects, issues, wiki pages, Git repositories, pull requests, notifications, and watching items.

How to use Backlog MCP Server?

Configure the server in your MCP‑compatible client using Docker (recommended) or a manual Node.js installation. Set environment variables BACKLOG_DOMAIN (your Backlog domain) and BACKLOG_API_KEY (your API key). Optional variables MAX_TOKENS and OPTIMIZE_RESPONSE control response size and field selection.

Key features of Backlog MCP Server

Project management (CRUD operations)
Issue tracking with comments
Wiki page management
Git repository management
Pull request management with comments
Notification and watching list management
GraphQL‑style field selection for optimized responses
Configurable token limiting for large responses

Use cases of Backlog MCP Server

List all projects and their details through natural language
Create, update, or delete issues with priority and type
Retrieve and filter issues by project or status
Manage pull requests, including creating and commenting
Fetch watching items and notification counts

常见问题

What are the dependencies and runtime requirements?

The server runs via Docker or Node.js (after building from source). You need a Backlog account with API access and a valid API key. Docker is the simplest deployment method.

Where does my data live?

All data remains in your Backlog space. The server is stateless; it only makes API calls to Backlog and does not store any data locally.

How can I limit response size or select only specific fields?

Set `MAX_TOKENS` (default 50 000) to cap token usage, and set `OPTIMIZE_RESPONSE=true` to enable GraphQL‑style field selection in your queries.

Can I customize tool descriptions or use a different language?

Yes. Create a `.backlog-mcp-serverrc.json` file in your home directory, or set environment variables (e.g., `BACKLOG_MCP_TOOL_ADD_ISSUE_COMMENT_DESCRIPTION`). A Japanese translation template is provided.

How do I keep the Docker image up‑to‑date?

Add `--pull always` to the Docker run arguments, or manually run `docker pull ghcr.io/nulab/backlog-mcp-server:latest`.

其他分类下的更多 MCP 服务器

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

der die das – German noun genders (Lingviko)

Lingviko

The article (der, die, das) of 90,000 German nouns, compounds included, plus a checker that finds wrong articles in German text (“mit der Zug” → dem). Uses dictionary data, not AI guessing. Free, no login.

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K