igloo-mcp
MCP server for searching and retrieving content from Igloo digital workplace instances. Enables AI assistants to search, fetch pages as Markdown, and look up member profiles via the Igloo API.
README
Igloo MCP Server
An MCP (Model Context Protocol) server that provides AI assistants with search capabilities for Igloo digital workplace instances.
Features
- Full-text search across Igloo communities
- Filter by application types, date ranges, archived content, and parent paths
- Sort results by views or relevance
- Fetch and convert pages to Markdown (single or multiple URLs)
- Search for members by name
- Fetch detailed member profiles and contact information
- Customizable server identity
Prerequisites
- Python 3.12 or higher
- uv package manager
- Access to an Igloo instance with API credentials
Installation & Usage
Quick Start (Direct Execution)
Run directly from GitHub without cloning:
uvx --from git+https://github.com/redhat-community-ai-tools/igloo-mcp igloo-mcp
Configure using environment variables (see Configuration below).
Local Development
Clone and install for local development:
git clone https://github.com/redhat-community-ai-tools/igloo-mcp.git
cd igloo-mcp
uv sync # Creates .venv/ and installs dependencies
igloo-mcp
Configuration
The server can be configured using:
- Environment variables (recommended for credentials):
IGLOO_MCP_*prefix - CLI arguments: kebab-case options (e.g.,
--server-name) .envfile: for local development
Example Configuration
Create a .env file in the project root:
# Required
IGLOO_MCP_COMMUNITY="https://your-igloo-instance.com"
IGLOO_MCP_COMMUNITY_KEY="10"
IGLOO_MCP_APP_ID="your-app-id"
IGLOO_MCP_APP_PASS="your-app-password"
IGLOO_MCP_USERNAME="your-username"
IGLOO_MCP_PASSWORD="your-password"
# Optional
IGLOO_MCP_SERVER_NAME="Your Organization Name"
IGLOO_MCP_LOG_LEVEL="INFO"
IGLOO_MCP_TRANSPORT="stdio"
IGLOO_MCP_PAGE_SIZE=50
IGLOO_MCP_DEFAULT_LIMIT=20
Configuration Parameters
Required:
IGLOO_MCP_COMMUNITY- Base URL of your Igloo communityIGLOO_MCP_COMMUNITY_KEY- Numeric identifier for your digital workplaceIGLOO_MCP_APP_ID- Application ID for the Igloo APIIGLOO_MCP_APP_PASS- Application password for the Igloo APIIGLOO_MCP_USERNAME- Username to authenticate withIGLOO_MCP_PASSWORD- Password to authenticate with
Optional:
IGLOO_MCP_SERVER_NAME(default: "Igloo") - Server name shown to clientsIGLOO_MCP_SERVER_INSTRUCTIONS(default: "Use this server to search and retrieve information from an Igloo instance.") - Instructions describing the server's purpose and capabilities to clients.IGLOO_MCP_LOG_LEVEL(default: "INFO") - Logging levelIGLOO_MCP_TRANSPORT(default: "stdio") - Transport protocol (stdio, streamable-http)IGLOO_MCP_HOST(default: "127.0.0.1") - Host address to bind the HTTP server to. Use "0.0.0.0" for Docker.IGLOO_MCP_PAGE_SIZE(default: 50) - Results per page (10-1000)IGLOO_MCP_DEFAULT_LIMIT(default: 20) - Default max search resultsIGLOO_MCP_PROXY- Optional proxy URLIGLOO_MCP_VERIFY_SSL(default: true) - Verify SSL certificatesIGLOO_MCP_FETCH_MAX_LENGTH(default: 50000) - Maximum Markdown content length per page (1000-500000)IGLOO_MCP_FETCH_TIMEOUT(default: 15.0) - Timeout in seconds for fetch requests (5.0-120.0)IGLOO_MCP_FETCH_MAX_PAGES(default: 5) - Maximum number of URLs per multi-URL fetch request (1-20)
Transport Options
By default, the server uses stdio transport. For HTTP transport, set IGLOO_MCP_TRANSPORT="streamable-http" - the server will be available at http://localhost:8000/mcp.
Available Tools
search_content
Search for content in the Igloo community with extensive filtering options.
Key Parameters:
query: Search query textapplications: Filter by type (blog, wiki, document, forum, gallery, calendar, pages, people, space, microblog)sort: Sort by "default" or "views"limit: Maximum results to returnupdated_date_type: Filter by date (past_hour, past_24_hours, past_week, past_month, past_year, custom_range)include_archived: Include archived content (default: false)
fetch_content
Fetch one or more pages from the Igloo community and convert to Markdown for LLM consumption.
Parameters:
url: A single URL string or a list of URLs to fetchmax_length: Maximum Markdown content length per page (optional, uses config default)start_index: Character offset to start reading from (optional). Use thenext_start_indexvalue from a previous truncated response to continue reading. Cannot be used withsection. Ignored for multi-URL requests.section: Name of section to jump to, e.g., "API Reference" (optional). Case-insensitive, fuzzy matches Markdown headers. Cannot be used withstart_index. Ignored for multi-URL requests.
Smart Truncation:
When content exceeds max_length, the response is truncated at semantic boundaries (paragraphs, sentences) rather than mid-sentence. Truncated responses include navigation metadata:
- Total document size and percentage shown
- List of remaining sections
- A
CONTINUEhint with the exactnext_start_indexcursor for seamless continuation
Example Workflow:
1. Agent: fetch_content(url="https://igloo.example.com/wiki/deployment")
Response: [content] + "CONTINUE: fetch_content(url="...", start_index=49801)"
2. Agent continues: fetch_content(url="...", start_index=49801)
OR jumps to section: fetch_content(url="...", section="Troubleshooting")
search_members
Search for members in the Igloo community by name. Returns basic information only.
Parameters:
query: Name or partial name to search for (e.g., "John Smith", "Jane")limit: Maximum number of members to return (default: 10)
Returns:
- List of matching members with basic info (name, email, member ID)
- Use the
member_idwithfetch_membersto get detailed profiles
Use Cases:
- Looking for someone by name
- Need to identify which member to get more information about
fetch_members
Get detailed profile information for one or more members by their ID(s).
Parameters:
members_ids: A list of member IDs (obtained fromsearch_membersresults)
Returns:
- Detailed member profile(s) including:
- Full name and email
- Job title and department
- Manager name
- Contact information (phone, office location)
- Profile URL
Example Workflow:
1. Agent: search_members(query="John Smith")
Response: [list of matching members with their member_ids]
2. Agent: fetch_members(members_ids=["12345-abcd-..."])
Response: [detailed profile for John Smith]
3. Agent: fetch_members(members_ids=["12345-abcd-...", "67890-efgh-..."])
Response: [detailed profiles for multiple members]
Docker
cp .env.example .env # Configure your credentials
docker compose up -d
The server will be available at http://localhost:8000/mcp with a health check at /health.
To run without compose:
docker build -t igloo-mcp .
docker run -p 8000:8000 --env-file .env igloo-mcp
Development
uv run pytest # Run tests
uv run mcp dev igloo_mcp/main.py # Test with MCP Inspector
License
See LICENSE file for details.
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。