Skip to main content
Glama
cheesecrust

Confluence MCP Server

by cheesecrust
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

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)

Related MCP server: Confluence Communication Server

설치

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.json에 다음을 추가합니다:

위 파일의 경로 macOS 기준:

  ~/Library/Application Support/Claude/claude_desktop_config.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
...

Available Tools

2 tools
confluence_get_pageC

Confluence 페이지 ID로 본문을 가져옵니다 (HTML을 텍스트로 변환).

ParametersJSON Schema
NameRequiredDescriptionDefault
pageIdYesConfluence page id
maxCharsNo본문 최대 길이

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool fetches and converts HTML to text, implying a read-only operation, but does not cover critical aspects like authentication requirements, rate limits, error handling, or output format (e.g., structured text). For a tool with no annotation coverage, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's core function and key transformation (HTML to text). It is front-loaded with the main purpose and avoids unnecessary details. However, it could be slightly more structured by explicitly naming parameters or usage scenarios, but it remains concise and to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (fetching and converting content), lack of annotations, and no output schema, the description is incomplete. It does not explain the return value (e.g., text format, potential truncation with 'maxChars'), error conditions, or dependencies like authentication. For a tool with these gaps, the description should provide more context to guide effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with clear documentation for both parameters: 'pageId' (Confluence page id) and 'maxChars' (본문 최대 길이, maximum length of body). The description adds minimal value beyond the schema, mentioning 'pageId' implicitly but not elaborating on parameter usage or constraints. With high schema coverage, the baseline score of 3 is appropriate as the description does not significantly enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Confluence 페이지 ID로 본문을 가져옵니다' (fetches page content by Confluence page ID) with the additional detail 'HTML을 텍스트로 변환' (converts HTML to text). This specifies the verb (fetch), resource (page content), and a key transformation (HTML to text). It distinguishes from the sibling 'confluence_search' by focusing on retrieval by ID rather than search functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'confluence_search'. It mentions the input parameter 'pageId' but does not explain prerequisites (e.g., needing a valid page ID) or exclusions (e.g., not for searching). Without explicit usage context or comparisons, the agent must infer when this tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv1.0.0
    • First observedconfluence_get_page
    • First observedconfluence_search
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0
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
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cheesecrust/confluence-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server