Content
This is a TypeScript-based server that integrates Backlog and Model Context Protocol (MCP). It implements the following key concepts of MCP:
- Resources representing Backlog projects (including URI and metadata)
- Tools for interacting with the Backlog API
- Prompts for generating summaries and analyses of Backlog data
## Features
### Resources
- Access Backlog projects via `backlog://project/[id]` URI
- Each project resource contains metadata and detailed information about the project
- JSON format resources for structured data access
- Access to issues within the project
- Access to Wiki pages within the project
### Tools
- `get_backlog_user` - Retrieve current Backlog user information
- `get_backlog_space` - Retrieve Backlog space information
- `list_recent_projects` - List recently viewed Backlog projects
- Configurable count and order
- `get_project_issues` - Retrieve issues for the project
- Filterable by status, assignee, pagination, etc.
- `get_issue_detail` - Retrieve detailed information for a specific issue
- `get_issue_comments` - Retrieve comments for an issue
- `add_issue_comment` - Add a comment to an issue
- `get_issue_comment_count` - Retrieve the number of comments for an issue
- `get_issue_comment` - Retrieve detailed information for a specific comment
- `get_wiki_page_list` - Retrieve a list of Wiki pages
- Filterable by project or keyword
- `get_wiki_page` - Retrieve detailed information for a specific Wiki page
- `update_wiki_page` - Update a Wiki page
### Prompts
- `summarize_projects` - Generate a summary of recently viewed Backlog projects
- `analyze_backlog_usage` - Analyze Backlog usage patterns based on user, space, and project data
- `summarize_wiki_pages` - Generate a summary of the project's Wiki pages
## Requirements
- A Backlog account with API access rights
- Environment variables:
- `BACKLOG_API_KEY`: Backlog API key
- `BACKLOG_SPACE_URL`: Backlog space URL (e.g., `https://your-space.backlog.com`)
## Development
Installing dependencies:
```bash
npm install
```
Building the server:
```bash
npm run build
```
Development with auto-rebuild:
```bash
npm run watch
```
## Installation
To use with Claude Desktop, add the server configuration:
MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
Windows: `%APPDATA%/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"mcp-backlog-server": {
"command": "/path/to/mcp-backlog-server/build/index.js",
"env": {
"BACKLOG_API_KEY": "your-api-key",
"BACKLOG_SPACE_URL": "https://your-space.backlog.com"
}
}
}
}
```
### Debugging
Debugging can be challenging as the MCP server communicates via standard input and output. It is recommended to use the [MCP Inspector](https://github.com/modelcontextprotocol/inspector). This is available as a package script:
```bash
npm run inspector
```
The Inspector provides a URL to access debugging tools in the browser.
## Technical Details
This server consists of the following main components:
- `index.ts` - Main entry point, initialization and configuration of the MCP server
- `backlog-client.ts` - Client that handles communication with the Backlog API
- `handlers/` - Handlers for resources, tools, and prompts
- `resource-handlers.ts` - Handling resources for projects, issues, and Wiki
- `tool-handlers.ts` - Interaction tools with the Backlog API
- `prompt-handlers.ts` - Prompt generation functionality
- `types.ts` - Type definitions for Backlog API responses
- `config.ts` - Loading configuration from environment variables
Connection Info
You Might Also Like
cc-switch
All-in-One Assistant for Claude Code, Codex & Gemini CLI across platforms.
awesome-claude-skills
A curated list of awesome Claude Skills, resources, and tools for...
claude-flow
Claude-Flow v2.7.0 is an enterprise AI orchestration platform.
vault
MCP prompt-injection scanning proxy — runtime security for MCP tool responses
ai-native-pm-os
The exhaustive guide to mastering Claude for Product Managers. Build your...
Train-in-Silence
The first Task-Aware MCP server and automated VRAM calculator for LLM...