About Backlog Mcp Server
Backlog Mcp Server provides read access to Backlog issues, comments, and files. The README notes that an official backlog-mcp-server has been released and recommends using it instead.
Key features
- 01Retrieve issue information
- 02Retrieve issue comments
- 03List issue attachments
- 04Download issue attachments
- 05List shared files
Use cases
- 01Review issue details from an MCP client
- 02Read comments associated with an issue
- 03Find or download issue attachments
MCP support
This project is an MCP server for retrieving Backlog issue data and files. Its README recommends using the official backlog-mcp-server instead.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y https://github.com/pj8/backlog-mcp-serverBACKLOG_API_TOKENSecretBACKLOG_SPACELocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README公式の backlog-mcp-serverがリリースされましたのでそちらをご利用ください。
Requirements
- Nodejs 20 以上, NPM 10 以上
機能
Install
- 下記のように backlog-mcp-server の設定を追加します。
- BACKLOG_API_KEY は、https://your-space.backlog.jp/EditApiSettings.action
- BACKLOG_DOMAIN は、 https://your-space.backlog.jp ならば、your-space.backlog.jp です
{
"mcpServers": {
"backlog": {
"autoApprove": [
"get_issue",
"get_issue_comments",
"get_issue_attachments",
"get_issue_attachment",
"get_issue_shared_files",
"get_issue_types"
],
"disabled": false,
"timeout": 60,
"command": "npx",
"args": [
"-y",
"https://github.com/shueisha-arts-and-digital/backlog-mcp-server"
],
"env": {
"BACKLOG_DOMAIN": "your-space.backlog.jp",
"BACKLOG_API_KEY": "****"
},
"transportType": "stdio"
}
}
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.