Backlog MCP Server

Name: Backlog MCP Server
Author: nulab

@nulab

Repository

About Backlog MCP Server

No overview available yet

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "backlog-mcp-server": {
      "command": "node",
      "args": [
        "build/index.js"
      ],
      "env": {
        "MCP_TRANSPORT": "http",
        "MCP_HTTP_PORT": "3333"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Backlog MCP Server?

A Model Context Protocol (MCP) server for interacting with the Backlog API. It provides tools for managing projects, issues, wiki pages, and more through AI agents such as Claude Desktop, Cline, and Cursor.

How to use Backlog MCP Server?

Configure your MCP client (e.g., Claude Desktop) by adding the server definition with either Docker or npx, setting the environment variables BACKLOG_DOMAIN (your Backlog domain) and BACKLOG_API_KEY. The server runs by default via stdio; you can also enable HTTP transport (streamable HTTP) using --transport http. Optionally, you can enable OAuth 2.0 authentication for per-user access by setting BACKLOG_OAUTH_CLIENT_ID, BACKLOG_OAUTH_CLIENT_SECRET, and MCP_SERVER_BASE_URL.

Key features of Backlog MCP Server

Project tools (create, read, update, delete)
Issue tracking and comments (create, update, delete, list)
Version/milestone management (create, read, update, delete)
Wiki page support
Git repository and pull request tools
Notification tools
GraphQL-style field selection for optimized responses
Token limiting for large responses

Use cases of Backlog MCP Server

Manage Backlog projects and issues through a conversational AI assistant
Track and comment on issues without leaving the chat interface
Update wiki pages or browse Git pull requests via natural language commands
Automate bulk operations like creating versions or listing notifications
Integrate Backlog into multi-tool agent workflows (e.g., combining with search or code tools)

FAQ from Backlog MCP Server

What transports does the server support?

It supports stdio (default) and HTTP transport (Streamable HTTP). To use HTTP, start with --transport http or set MCP_TRANSPORT=http.

How do I enable OAuth authentication?

Set BACKLOG_OAUTH_CLIENT_ID, BACKLOG_OAUTH_CLIENT_SECRET, and MCP_SERVER_BASE_URL (public server URL). The server then exposes OAuth endpoints for MCP clients to authenticate each user independently.

Can I enable only some toolsets?

Yes, use the --enable-toolsets flag or ENABLE_TOOLSETS environment variable with a comma-separated list of toolset names (e.g., space,project,issue). By default, all toolsets are enabled.

What environment variables are required?

BACKLOG_DOMAIN and BACKLOG_API_KEY are required for API‑key auth. For HTTP transport, you can set MCP_TRANSPORT, MCP_HTTP_HOST, MCP_HTTP_PORT, and related variables.

What are the limitations of OAuth mode?

OAuth mode currently supports only a single Backlog organization; multi‑organization configuration is not compatible. Client registrations and tokens are stored in memory and lost on server restart.