Igloo MCP
Igloo MCP - Snowflake MCP Server for agentic querying
Installation
npx igloo-mcpAsk AI about Igloo MCP
Powered by Claude Β· Grounded in docs
I know everything about Igloo MCP. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
Igloo MCP
A lightweight Snowflake MCP server that connects your AI assistant to Snowflake with built-in safety, caching, and auditing. Query databases, build catalogs, and create living reportsβall through natural language.
Why Igloo MCP?
π Query Safely
Block dangerous DDL/DML by default, auto-cancel slow queries, and log every execution. Use execute_query with configurable guardrails and test_connection to validate authentication before running queries.
β‘ Work Faster
Minimize token usage through progressive disclosure and smart result caching. Tools like get_report support multiple retrieval modes (summary/sections/insights/full), and search_catalog lets you find tables without hitting Snowflake.
π Stay Audited
Maintain complete query history with source attribution for compliance tracking. Every execute_query call logs to history, and Living Reports track all modifications with full audit trails via evolve_report.
π Build Living Reports
Create auditable, evolving business reports with create_report, modify them safely with evolve_report, attach charts to insights, and export to HTML/PDF/Markdown via render_report.
Quick Start
Prerequisites
# Install igloo-mcp
uv pip install igloo-mcp
# Configure Snowflake connection (uses Snowflake CLI)
snow connection add --connection-name quickstart --account <account> --user <user> --authenticator externalbrowser --warehouse <warehouse>
Cursor Setup
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"igloo-mcp": {
"command": "igloo_mcp",
"args": ["--profile", "quickstart"]
}
}
}
Restart Cursor and ask: "Preview the customers table"
Claude Code Setup
Run from terminal:
claude mcp add --scope user --transport stdio igloo-mcp -- igloo_mcp --profile quickstart
Or add to ~/.claude.json manually:
{
"mcpServers": {
"igloo-mcp": {
"type": "stdio",
"command": "igloo_mcp",
"args": ["--profile", "quickstart"]
}
}
}
Restart Claude Code and ask: "Show me the schema for my database"
Note: The executable is
igloo_mcp(underscore), notigloo-mcp(dash).
Full setup guide: docs/installation.md
Core Tools
π Query & Explore
| Tool | Description |
|---|---|
execute_query | Run SQL with guardrails, timeouts, and auto-insights |
build_catalog | Export Snowflake metadata for offline search |
search_catalog | Find tables/columns without querying Snowflake |
build_dependency_graph | Visualize table lineage and dependencies |
π Living Reports
| Tool | Description |
|---|---|
create_report | Initialize auditable JSON-backed reports |
evolve_report | Modify reports with LLM assistance and audit trail |
evolve_report_batch | Perform multiple operations atomically |
render_report | Export to HTML, PDF, or Markdown via Quarto |
get_report | Read reports with progressive disclosure modes |
search_report | Find reports by title or tags |
search_citations | Search citations by source type or provider |
get_report_schema | Discover valid structures and section templates at runtime |
validate_report | Quality checks: citations, empty sections, stale content |
π₯ Health & Diagnostics
| Tool | Description |
|---|---|
test_connection | Validate Snowflake authentication |
health_check | Monitor server, profile, and catalog status |
View all 16 tools: docs/api/TOOLS_INDEX.md
When to Use Igloo MCP
| Choose Igloo MCP | Choose Snowflake Labs MCP |
|---|---|
| AI assistant for dev/analytics workflows | Production Cortex AI integration |
| Simple SnowCLI-based setup | Enterprise service architecture |
| Query safety + automatic caching | Full Snowflake object management |
| Built-in auditing and compliance | Container-based deployment |
Resources
- π Getting Started Guide
- π§ API Reference
- π Living Reports User Guide
- π‘ Examples
- π Changelog
- π¬ Discussions
MIT Licensed | Built for agentic efficiency
