Skip to main content
Glama
README.md
# Confluence MCP Server

Confluence API를 사용하여 페이지 검색 및 조회 기능을 제공하는 MCP(Model Context Protocol) 서버입니다.

## 기능

### Tools

| Tool | 설명 |
|------|------|
| `confluence_search` | CQL을 사용하여 Confluence에서 페이지를 검색합니다 |
| `confluence_get_page` | 페이지 ID로 본문을 가져옵니다 (HTML을 텍스트로 변환) |

## 설치

```bash
npm install
npm run build
```

### Personal Access Token 발급

1. Confluence 설정 > Personal Access Tokens 이동
2. "Create token" 클릭
3. 토큰 이름 입력 후 생성

## Claude Desktop 설정

`claude_desktop_config.json`에 다음을 추가합니다:

위 파일의 경로 
macOS 기준:
```
  ~/Library/Application Support/Claude/claude_desktop_config.json
```

```json
{
  "mcpServers": {
    "confluence": {
      "command": "node",
      "args": ["/path/to/confluence-mcp/dist/server.js"],
      "env": {
        "CONFLUENCE_BASE_URL": "https://your-domain.atlassian.net",
        "CONFLUENCE_PAT": "your-personal-access-token"
      }
    }
  }
}
```

> `.env` 파일 대신 위처럼 `env` 필드에 직접 설정해도 됩니다.

## 사용 예시

1. mcp server 를 실행한다.
2. claude desktop을 킨후 `+` 커넥터를 보고 연동이 되었는지 확인 합니다.
  (이때 안 켜졌다면 claude desktop을 완전히 종료 후 실행)
3. 그 후 claude desktop 채팅창에 아래와 같이 검색합니다.

**페이지 검색:**
```
Confluence에서 관련 문서를 검색해줘
playMcp 관한 내용 찾아줘
...
```

TDQS

B3.1/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one retrieves a specific page by ID, while the other searches for pages by keyword using CQL. There is no overlap in functionality, making it easy for an agent to choose the correct tool based on whether it needs to fetch a known page or find pages matching a query.

Naming Consistency5/5

Both tools follow a consistent 'confluence_verb_noun' pattern (confluence_get_page, confluence_search), using snake_case and starting with the domain prefix. This predictable naming scheme enhances readability and reduces cognitive load for agents.

Tool Count2/5

With only 2 tools, the server feels severely under-scoped for a Confluence integration. A typical content management system like Confluence would require CRUD operations (create, update, delete pages), management of spaces or attachments, and more advanced querying. This minimal set limits agent capabilities significantly.

Completeness2/5

The toolset is highly incomplete for a Confluence server. While it covers basic retrieval and search, it lacks essential operations such as creating, updating, or deleting pages, managing comments or attachments, and handling spaces. This creates significant gaps that will cause agent failures in common workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues