- TABLES
- SOURCES
- SINKS
- HUMAN
Short answer
How can I map my RisingWave environment with AI?
Your AI uses specific tools to pull lists of your tables, sources, and sinks. This gives you a clear view of your streaming data architecture without writing SQL. You'll get a full breakdown of your topology below.
The results.
Where your data maps land.
The AI organizes your environment into three distinct categories.
TABLES
Schema overview
The AI identifies every table currently in your RisingWave instance. You get a clean list of names and structures.
SOURCES
Ingestion points
The AI finds where your data is coming from. It maps out the external inputs feeding your streams.
SINKS
Output destinations
The AI tracks where your processed data is being sent. This shows you the end of your data pipelines.
HUMAN
Manual verification
The AI provides the list, but you decide if the topology matches your intended architecture. You handle the actual data modeling.
The workflow
What your AI does when the request arrives.
The AI acts as a bridge between your natural language questions and the RisingWave engine.
Identify tables
The AI scans your database to find all existing tables. It builds a list of what's available for querying.
list_tablesLocate sources
The AI checks your ingestion layer. It identifies the specific sources feeding your streaming environment.
list_sourcesFind sinks
The AI looks at your output layer. It finds the destinations where your data is being written.
list_sinksMap connections
The AI combines these lists to explain how data flows from a source to a sink through your tables. It uses the gathered lists to build a mental model of your setup.
list_tableslist_sourceslist_sinks
Try it
Copy these to start.
Use these prompts to begin exploring your RisingWave environment.
Starting points
These are basic starting lines. Swap out specific names if you want to focus on one part of your setup.
RisingWave Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_POZ197YoiA8LB1iU15GyiwF0QcgyMosQUQ2XSBMS/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — RisingWave capabilities are ready to use.
{
"mcpServers": {
"risingwave-streaming-database-mcp": {
"url": "https://edge.vinkius.com/vk_preview_POZ197YoiA8LB1iU15GyiwF0QcgyMosQUQ2XSBMS/mcp"
}
}
}List all the tables in my RisingWave database.
What sources are currently configured in my environment?
Show me all the sinks where my data is being sent.
Can you give me a summary of my entire data topology including sources, tables, and sinks?
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect RisingWave once, then ask.
Just link your account once. Your credentials stay encrypted, and you can immediately start asking questions in your preferred AI client.
Connect RisingWave to your AIFAQ
How this task behaves
- 01
Can the AI change my table schemas?
No. The AI can only read the existing structure using the provided tools. It cannot create, drop, or alter tables.
- 02
Can the AI delete my data sources?
No. This MCP is read-only for topology exploration. It cannot delete or modify your sources or sinks.
- 03
Does the AI see the actual data inside my tables?
No. The tools used here only list the metadata, such as table names and source types, not the row-level data.
- 04
How does the AI know which tables exist?
It uses the list_tables tool to fetch the names of all tables in your RisingWave instance.
- 05
Can I use this to run complex SQL queries?
No. This specific task is for exploring the topology and structure of your environment.
More questions about RisingWave? The Connector page answers them. See everything the RisingWave Connector can do
Connect RisingWave to Claude, Cursor, ChatGPT & more
