Metabase MCP server provides integration with the Metabase API, enabling LLM with MCP capabilites to directly interact with your analytics data, this server acts as a bridge between your analytics platform and conversational AI.
git clone https://github.com/hluaguo/metabase-mcp.gitMetabase MCP Server is a Model Context Protocol integration that bridges AI assistants (Claude, Cursor, and other MCP clients) with your Metabase business intelligence platform. It enables you to query databases, execute SQL and MongoDB queries, manage dashboards, and explore data through natural language without leaving your AI assistant. The server supports secure API key authentication, handles complex database operations like table discovery and field inspection, and provides context-aware logging for reliable production use. Teams can automate analytics workflows, generate reports, and answer data questions conversationally by leveraging their existing Metabase instance.
["Ensure the Metabase MCP server is installed and configured with your Metabase instance credentials. Verify connectivity by running a simple query like 'List all dashboards.'","Identify the [METABASE_DASHBOARD_ID] and [SPECIFIC_METRICS] you need. Use Metabase's UI to locate the dashboard ID in the URL (e.g., `http://your-metabase-instance.com/dashboard/123`).","Specify the date range ([START_DATE] and [END_DATE]) and any filters (e.g., region, product category) using the `filter` parameter in the query. For example: `filter: { \"region\": \"North America\" }`.","Execute the query and review the results. Use the output to generate reports, identify trends, or trigger follow-up actions in your workflow (e.g., updating a CRM or Slack channel).","For advanced use, chain multiple queries to compare datasets or combine results from different dashboards. Use the `join` or `union` operations if supported by the MCP server."]
Execute SQL queries and retrieve analytics data through Claude or Cursor without switching applications
Automate business intelligence workflows by creating and managing Metabase cards programmatically
Explore database schemas and table structures using natural language questions
Run MongoDB aggregation pipelines directly from AI assistants for document database analytics
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/hluaguo/metabase-mcpCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Use the Metabase MCP server to query [METABASE_DASHBOARD_ID] for [SPECIFIC_METRICS] between [START_DATE] and [END_DATE]. Format the results as a markdown table with columns for [COLUMN_NAMES]. Include a brief analysis of trends or outliers in the data.
### Sales Performance Analysis (Q2 2024) | Region | Total Sales | Avg. Deal Size | Conversion Rate | Top Product Category | |--------------|-------------|----------------|-----------------|----------------------| | North America| $2.4M | $12,500 | 22% | Enterprise SaaS | | EMEA | $1.8M | $9,800 | 18% | Mid-Market Solutions | | APAC | $1.2M | $7,200 | 15% | SMB Tools | **Key Insights:** 1. **North America** leads in both total sales ($2.4M) and average deal size ($12,500), likely due to strong enterprise adoption. The conversion rate of 22% is also the highest, suggesting effective sales strategies in this region. 2. **EMEA** shows a balanced performance with $1.8M in sales but a lower average deal size ($9,800) and conversion rate (18%). This may indicate a need for targeted upselling strategies or localized marketing campaigns. 3. **APAC** lags in all metrics, with the lowest total sales ($1.2M), average deal size ($7,200), and conversion rate (15%). Further investigation into regional preferences or competitive pressures is recommended. **Recommendations:** - Prioritize North America for high-value deals and allocate additional resources to EMEA to improve conversion rates. - Explore why APAC underperforms and consider piloting localized sales tactics or product adaptations. - Investigate the top product categories in each region to identify cross-selling opportunities.
Empower your team with open-source analytics
Cookie-free analytics with heatmaps and surveys
A/B testing for physical stores
Privacy-first analytics for modern businesses
Data science and analytics knowledge
Custom behavioral analytics for web traffic
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan