mcpField
M
mcp-server-backlog

mcp-server-backlog

Local
github.com/kazuhideokiProductivity0Updated 77w ago
Repository

About mcp-server-backlog

mcp-server-backlog is an MCP server for accessing Backlog through its API. It supports read-only or full mutation permissions, with the API key stored in a project-root file.

Key features

  1. 01Read Backlog data
  2. 02Choose read-only or mutation access
  3. 03Configure permissions with a CLI flag
  4. 04Build and run with Node.js

Use cases

  1. 01Allow an assistant to read Backlog data
  2. 02Restrict an integration to GET operations
  3. 03Enable changes through Backlog API endpoints

MCP support

Exposes Backlog API access to MCP clients. The READ permission allows GET endpoints only; MUTATE enables POST, PUT, PATCH and DELETE as well.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-server-backlog

TODO

  • フラグ渡すとこリファクタ
  • apikey を CLI から渡せるようにする
  • spaceId ふくめ、URL を CLI から渡せるようにする

How to use

Setup

Set Backlog Api Key to apikey file in the project root.

Dependencies install & Build
npm install
npm run build
Add MCP Server to Claude Code
claude mcp add backlog node /path/to/mcp-server-backlog/dist/index.js -- --permission READ
Running the Server
# Development mode with permission flag
npm run dev -- --permission READ
# Production mode with permission flag (after build)
node /path/to/mcp-server-backlog/dist/index.js --permission READ
Permission Levels
  • READ: Read-only access (can only use GET endpoints)
  • MUTATE: Full access (can use all endpoints including POST, PUT, PATCH, DELETE)

Comments

Markdown supported

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.