# RisingWave MCP for AI Agents AI Agent Connect

> RisingWave lets you manage your streaming database directly through your AI agent. You can run SQL queries, pipe in JSON events, and check the status of your materialized views or data sinks without switching tabs. It connects your real-time data pipelines to your workspace, allowing you to monitor streaming logic and ingest test data through natural conversation.

## Overview
- **Category:** databases
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_POZ197YoiA8LB1iU15GyiwF0QcgyMosQUQ2XSBMS/ai-agent-connect
- **Tags:** streaming-database, real-time-analytics, sql, event-ingestion, materialized-views

## Description

RisingWave lets you manage your streaming database directly through your AI agent. Managing a streaming database usually means jumping between a CLI, a web console, and your IDE just to check if a pipeline is healthy or to run a quick query. This RisingWave MCP changes that by bringing the database into your chat window. Instead of hunting for the right endpoint, you just tell your agent to show you the current state of your materialized views or to push a test batch of events. It handles the heavy lifting of connecting to the RisingWave HTTP API so you can focus on the logic. By adding this to the Vinkius catalog, you get a way to interact with your real-time data flow as easily as sending a message. You can debug DDL changes on the fly or quickly see what sources your sinks are pulling from. It turns a multi-step manual process into a conversation. You no longer have to keep a dozen tabs open just to see if your data is moving. If you need to run a query to check a specific record, you just ask. If you need to see if your sinks are correctly configured, the agent can pull that list for you instantly. It creates a much smoother loop for developers who need to stay in the flow of building real-time features.

## Tools

### execute_sql
Run any SQL statement against your database. Use this to create new tables or perform quick data updates.

### ingest_events
Send JSON objects or arrays into a specific table. This is the fastest way to feed test data into your streams.

### list_materialized_views
See all your active materialized views. Use this to check the status of your real-time aggregations.

### list_sinks
Get a list of all configured data sinks. This lets you see where your data ends up after processing.

### list_sources
View all external data sources. Use this to map out how data enters your streaming pipeline.

### list_tables
See a list of all your user tables in RisingWave. This helps you get oriented quickly when exploring a new environment.

## Prompt Examples

**Prompt:** 
```
List all the materialized views currently active in RisingWave.
```

**Response:** 
```
I've checked your RisingWave catalog. You have 3 active materialized views: **daily_sales_summary**, **user_login_stats**, and **realtime_inventory_levels**. Which one do you want to look at?
```

**Prompt:** 
```
Ingest this JSON event into the 'user_activity' table: {"user_id": 123, "action": "login"}.
```

**Response:** 
```
I've sent that event to the **user_activity** table. It's now available for streaming processing in your pipeline.
```

**Prompt:** 
```
Show me all external data sinks configured in the system.
```

**Response:** 
```
Checking your configuration now. I found 2 configured sinks:

* **s3_archived_logs** (S3)
* **postgres_reporting_db** (JDBC)
```

## Capabilities

### Run SQL commands
Execute DDL and DML statements like CREATE and INSERT directly through your agent.

### Push JSON events
Send single or bulk JSON objects into your tables instantly to test your pipelines.

### View data topology
See a full list of your tables and materialized views in one clear overview.

### Check data sinks
Identify where your processed data is being sent by listing all configured sinks.

### Inspect data sources
View all external data sources currently feeding into your streaming environment.

### Monitor pipeline state
Get a clear look at the status of your active streaming views and data flows.

## Use Cases

### Debugging a stuck pipeline
A data engineer asks the agent to list materialized views to see if a specific view is lagging or failing to update.

### Testing a new API
A backend dev uses `ingest_events` to push a mock JSON payload and see if it hits the database correctly.

### Schema Discovery
An analyst asks the agent to list all sources to understand what external data is available for a new dashboard.

### Quick DDL changes
A developer uses `execute_sql` to add a column to a table during a hotfix without opening a separate SQL tool.

## Benefits

- Run SQL queries faster: Use `execute_sql` to perform DDL and DML operations without leaving your editor.
- Faster test data ingestion: Use `ingest_events` to push JSON payloads into your tables instantly.
- Better topology awareness: Use `list_tables` and `list_sources` to see how data flows from start to finish.
- Easier view monitoring: Use `list_materialized_views` to check the health of your real-time aggregations.
- Quick sink auditing: Use `list_sinks` to verify where your data is being exported in seconds.

## How It Works

The bottom line is you get a direct line to your streaming database without leaving your workspace.

1. Connect your RisingWave URL in your AI client.
2. Tell your agent to list your current tables or views.
3. Receive a formatted summary of your streaming data environment.

## Frequently Asked Questions

**What can I do with the RisingWave MCP?**
You can manage your streaming database using natural language. This includes running SQL queries, ingesting JSON events, and listing your tables, sources, and sinks.

**How do I use RisingWave to test my data?**
You can use the event ingestion tool to push test JSON objects into your tables. This lets you see how your pipeline handles new data without manual CLI work.

**Can I run SQL queries through the RisingWave MCP?**
Yes, you can execute DDL and DML statements like CREATE, SELECT, and INSERT directly through your AI client.

**How does this help with streaming pipelines?**
It gives you a way to monitor your materialized views and data sinks quickly. You can see the status of your real-time data flow without switching apps.

**Can I see my data sources?**
Yes, the Connector can list all external data sources connected to your RisingWave instance so you can see your data topology.

**Is this for production databases?**
It is designed to help you manage and interact with your RisingWave streaming database. It's great for both development testing and production monitoring.

**Can I run complex JOIN queries on my materialized views?**
Yes! Use the `execute_sql` tool to run any valid RisingWave SQL query. You can perform complex analytical queries or inspect the results of your real-time aggregations.

**How do I check if my Kafka or Pulsar sources are correctly connected?**
Use the `list_sources` tool. It queries the internal catalog to provide a list of all external data sources currently configured in your RisingWave instance.

**Is there a way to push data directly into a table without using an external source?**
Absolutely. Use the `ingest_events` tool to send JSON objects or arrays directly to a specific table via the Events API, perfect for testing or low-latency ingestion.