inhouse_confluence_mcp
An MCP server implementation for interacting with self-hosted Confluence Data Center or Server instances via search, content retrieval, and optional write operations. It features space auto-discovery, audit logging, and granular access control for secure enterprise collaboration.
README
inhouse_confluence_mcp
In-house Confluence (Data Center/Server) MCP server implementation. Default mode is read-only, and write tools are controlled by policy.
Tools
confluence_list_spacesconfluence_search_cqlconfluence_get_contentconfluence_get_labelsconfluence_get_childrenconfluence_get_attachmentsconfluence_get_commentsconfluence_scan_contentconfluence_get_likes(experimental, off by default)confluence_create_page(write, off by default)confluence_update_page(write, off by default)confluence_add_label(write, off by default)confluence_add_comment(write, off by default)
Quick Start
- Copy
.env.exampleto.env - Set required values:
CONFLUENCE_BASE_URLCONFLUENCE_AUTH_MODE(patorbasic)CONFLUENCE_PATorCONFLUENCE_USERNAME/CONFLUENCE_PASSWORD
- Install and run:
python -m pip install -e .
confluence-mcp
Or:
python -m confluence_mcp.main
OpenCode Registration
Use OpenCode local MCP config with a command array and environment object.
{
"mcp": {
"inhouse-confluence": {
"type": "local",
"command": [
"C:\\Users\\jae_chul.lee\\inhouse_confluence_mcp\\.venv\\Scripts\\python.exe",
"-m",
"confluence_mcp.main",
"--env-file",
"C:\\Users\\jae_chul.lee\\inhouse_confluence_mcp\\.env"
],
"environment": {
"PYTHONIOENCODING": "utf-8"
}
}
}
}
Notes:
- Do not rely on
Activate.ps1in MCP commands. - Prefer direct venv python path.
--env-filemakes startup independent fromcwd.- Optional override: set
CONFLUENCE_MCP_ENV_FILEinenvironment.
.env Loading Rules
On startup, the server looks for .env in this order:
--env-filepathCONFLUENCE_MCP_ENV_FILE- Current working directory (
.env,.env.local) - Python executable neighborhood (useful for
.venvlayout) - Project/module directory
If no file is found, startup logs searched paths.
Space Auto-Discovery
- If
ALLOWED_SPACESis empty andAUTO_DISCOVER_SPACES=true, the server auto-loads available space keys on startup. DENIED_SPACESis optional. Use it only when you need an explicit sensitive-space blocklist.- To generate a ready-to-copy env line manually:
confluence-mcp-sync-spaces
- Output file:
logs/spaces_discovered.json
Recommended Settings
- Keep
WRITE_ENABLED=falseinitially - Configure
ALLOWED_SPACESfirst - Add
DENIED_SPACESonly for sensitive spaces - Keep
EXPERIMENTAL_LIKES=falseunless needed
Logs
- Audit log path:
AUDIT_LOG_PATH(default:logs/audit.jsonl) - Fields: timestamp, tool, status, latencyMs, traceId, error
Tests
python -m unittest discover -s tests -v
Tool Probe on Startup
- By default, the server probes API permissions at startup and exposes only reachable tools.
- Toggle all probes with
TOOL_PROBE_ON_STARTUP=true|false. - Disable only space probe with
SPACE_PROBE_ON_STARTUP=false. - When
SPACE_PROBE_ON_STARTUP=false, user-declaredALLOWED_SPACESis trusted for policy checks. - If
/rest/api/spaceis blocked,confluence_list_spacesis hidden. - If
/rest/api/content/searchis blocked, read/write content tools are hidden.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。