mcp
MCP server for querying data warehouses (BigQuery, Snowflake, Redshift, Azure Synapse) using natural language. Connect your favorite AI assistant (Claude, Mistral, ChatGPT, Copilot, Gemini) to your marketing analytics and get SQL-powered insights in seconds.
Documentation
Quanti MCP Server
MCP server to query your data warehouse (BigQuery, Snowflake, Redshift, Azure Synapse) with natural language. Connect Claude, ChatGPT, Copilot or Gemini to your marketing data and get instant SQL insights.
Features
- Natural Language to SQL: Ask questions in plain language, get SQL queries executed on your data warehouse
- Multi-platform Support: Works with BigQuery, Snowflake, Redshift, and Azure Synapse
- AI Assistant Compatible: Connect to Claude, ChatGPT, Gemini, Le Chat, or Copilot
- Schema Discovery: Automatic schema detection and context building via RAG
- Use Case Library: Save and reuse your favorite analyses
- Secure: OAuth 2.0 authentication, read-only queries, per-project access control
Quick Start
Server URL
https://ai.quanti.io/mcpSetup Guides
Available Tools
| Tool | Description |
|---|---|
| `list_projects` | List your accessible Quanti projects |
| `get_project_context` | Get project context (connectors, datasets, date ranges) |
| `get_schema_context` | Build schema context for your question using RAG |
| `execute_query` | Execute read-only SQL queries on your data warehouse |
| `get_use_cases` | Search for relevant use case templates |
| `list_my_use_cases` | List your personal saved analyses |
| `list_project_use_cases` | List team shared analyses |
| `create_use_case` | Save an analysis for reuse |
| `update_use_case` | Update an existing use case |
| `delete_use_case` | Delete a use case |
| `collect_feedback` | Provide feedback on query results |
How It Works
1. Connect your AI assistant to the Quanti MCP server
2. Authenticate with your Quanti account via OAuth 2.0
3. Ask questions in natural language about your marketing data
4. The server builds context from your data warehouse schema
5. Your AI assistant generates and executes SQL queries
6. Get insights with formatted results
Example Queries
What are my top 10 campaigns by conversions this month?Show me the daily spend trend for Google Ads over the last 30 daysCompare performance between Meta and Google Ads campaignsSupported Data Sources
Quanti connects to 50+ marketing data sources including:
- Advertising: Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, Microsoft Ads
- Analytics: Google Analytics 4, Adobe Analytics
- CRM: Salesforce, HubSpot
- E-commerce: Shopify, WooCommerce
- And many more...
Requirements
- Quanti account with access to at least one project
- Data warehouse with indexed schema (BigQuery, Snowflake, Redshift, or Azure Synapse)
- AI assistant with MCP support (ChatGPT, Claude, Gemini, Le Chat, Copilot)
MCP Protocol
This server implements the Model Context Protocol (MCP) specification:
- Protocol Version: 2024-11-05
- Transport: HTTP with SSE (Server-Sent Events)
- Authentication: OAuth 2.0 with dynamic discovery
Support
- Documentation: docs.quanti.io
- Email: support@quanti.io
- Website: quanti.io
License
MIT License - see LICENSE for details.
Made with ❤️ by Quanti
Frequently asked questions
What is mcp?
mcp is MCP server for querying data warehouses (BigQuery, Snowflake, Redshift, Azure Synapse) using natural language. Connect your favorite AI assistant (Claude, Mistral, ChatGPT, Copilot, Gemini) to your marketing analytics and get SQL-powered insights in seconds.
How do I install mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp open source?
Yes — it is hosted on GitHub at https://github.com/quantiio/mcp.
Related MCP tools
serversModel Context Protocol Servers
codegraphPre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
goosean open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
metabaseThe easy-to-use open source Business Intelligence and Embedded Analytics tool that lets everyone work with data :bar_chart:
UI-TARS-desktopThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
cogneeCognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP