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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.