# Metaplane MCP for AI Agents AI Agent Connect > Metaplane MCP for data observability. It lets you track monitors, manage incidents, and check data quality metrics through your AI client. Instead of digging through dashboards, you can just ask your agent to tell you what's broken or check the status of your data pipelines in seconds. It connects your Metaplane account to your agent so you can manage data health through natural conversation. ## Overview - **Category:** data-analytics - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_ZzPtEvduP33DM4pFjpxFzBv2qdMoX1IaKAzD75wY/ai-agent-connect - **Tags:** data-quality, data-observability, incident-management, data-pipelines, monitoring, alerts ## Description Managing data quality usually feels like a game of whack-a-mole. You're constantly switching tabs to see if a pipeline finished, why a specific monitor failed, or what the latest incident status is. This Connector changes that by putting your Metaplane data directly into your AI's context. You can ask your agent to summarize recent incidents, check the health of a specific monitor, or even see what schemas are connected to your warehouse. It turns your data observability into a conversation. Because Vinkius hosts this Connector, you can get it running in your preferred client in minutes. You stop hunting for information and start getting answers about your data health immediately. You can quickly see if a production table is empty or if a new schema is actually live before you start building a report. It takes the friction out of monitoring your data stack, letting you focus on fixing problems rather than finding them. ## Tools ### list_monitors See every data monitor currently configured in your account. This helps you see your full monitoring coverage. ### list_connection_schemas List all schemas for a specific data connection. Use this to verify that your tables are visible. ### trigger_monitor_run Manually start a monitor run to check data quality right now. This is great for manual validation. ### get_account_info Get your current account details from Metaplane. Use this to verify your connection status. ### get_incident Fetch the specific details for a single data incident. This helps you see the exact error message. ### get_monitor Retrieve the full metadata and status for a specific monitor. Use this to see if a check passed. ### get_monitor_runs Look up the history of runs for a particular monitor. This shows you the trend of your data quality. ### list_configured_alerts See a list of all your active alert configurations. Use this to audit your notification rules. ### list_data_connections View every data source connection you have set up. This gives you a high level view of your stack. ### list_incidents Get a full list of all your data incidents. Use this to see what's currently broken across your data. ## Prompt Examples **Prompt:** ``` List all my data monitors in Metaplane. ``` **Response:** ``` Retrieving monitors... I found 5 active monitors including **Postgres Row Count** and **Snowflake Schema Change**. | Monitor Name | Status | Last Run | | :--- | :--- | :--- | | Postgres Row Count | ✅ Healthy | 2 mins ago | | Snowflake Schema Change | ⚠️ Warning | 5 mins ago | ``` **Prompt:** ``` Show recent incidents for the last 24 hours. ``` **Response:** ``` Checking incidents... There is one active high-severity incident: * **Issue**: Null values detected in production.users * **Severity**: High * **Status**: Investigating * **Details**: The users table in the production warehouse is returning nulls for the primary key. ``` **Prompt:** ``` Trigger a run for monitor ID 'mon_12345'. ``` **Response:** ``` Triggering run... Monitor **mon_12345 (Postgres Volume)** has been started and is currently processing. I'll let you know if it completes successfully. ``` ## Capabilities ### Check monitor health See the current status and metadata of any configured data monitor. ### Look up incidents Pull up the full history and resolution details for data quality alerts. ### Run a monitor Trigger a manual check on a data pipeline to validate quality on demand. ### See data connections View all connected databases, warehouses, and schemas in one place. ### Review alert rules Inspect your active notification settings and alert configurations. ## Use Cases ### Debugging a failed pipeline An engineer asks the agent to list_incidents for the last hour to see why a production table is empty. ### Verifying a new warehouse connection A dev uses list_connection_schemas to confirm that the new Snowflake schemas are visible to the agent. ### Auditing monitor health A manager asks the agent to list_monitors to see which ones are currently running and which are failing. ### Manual quality check A user triggers a specific check using trigger_monitor_run to get an immediate status update before pushing a major code change. ### Checking alert settings A data ops lead uses list_configured_alerts to make sure the production alerts aren't being silenced or misconfigured. ## Benefits - Get faster incident resolution by using list_incidents to quickly identify high_priority issues. You won't have to hunt through multiple pages to see what's broken, letting you jump straight to the fix. - Understand your data lineage better by using list_data_connections and list_connection_schemas. It gives you a clear view of every warehouse and schema connected to your account in one place. - Verify data integrity on demand by using trigger_monitor_run to run a check whenever you need it. This is perfect for verifying a pipeline before a big release or after a manual data fix. - Keep your team informed by using list_configured_alerts to audit and manage your notification rules easily. You can ensure the right people get the right alerts without digging into complex settings. - Reduce context switching by using get_monitor to check health statuses directly within your agent's chat window. You can see the metadata and status of any monitor without leaving your current workflow. - Access your account details quickly by using get_account_info to confirm your current setup. This helps you stay organized when managing multiple environments or different data sources. ## How It Works The bottom line is you get instant answers about your data quality without leaving your chat interface. 1. Subscribe to the Connector on Vinkius. 2. Add your Metaplane API key to the configuration. 3. Ask your agent to list incidents or check monitor health. ## Frequently Asked Questions **What is the Metaplane MCP for?** It's for managing your data quality and observability. You can ask your agent to check monitor statuses, find incidents, and view your data connections. **Can I use Metaplane MCP to see my database schemas?** Yes, you can use it to list schemas for any of your connected data sources. This helps you understand your data lineage without leaving your chat. **How do I check for recent data incidents with Metaplane MCP?** Just ask your agent to list your incidents. It will pull the latest alerts and give you a summary of what's broken and its current status. **Can I manually run a data check using Metaplane MCP?** Yes, you can trigger a specific monitor run on demand. This is great for verifying data quality before a big release. **Does Metaplane MCP work with Claude or Cursor?** Yes, it works with any MCP-compatible client like Claude, Cursor, or Windsurf. You just need to connect your Metaplane API key. **How do I find my Metaplane API Key?** Log in to Metaplane, go to your Account Settings, and you can generate or copy your API Key from the API section. **Can I trigger a monitor run manually?** Yes! Use the `trigger_monitor_run` tool and provide the monitor ID to start a data quality check immediately. **Is my data observability data secure?** Absolutely. Your token is encrypted at rest and injected securely at runtime.