AWS officially releases Aurora MySQL MCP Server! Query execution in natural language
This is Onkai Yuta (@fat47) from the Service Reliability Group (SRG) of the Media Headquarters.
#SRG(Service Reliability Group) is a group that mainly provides cross-sectional support for the infrastructure of our media services, improving existing services, launching new ones, and contributing to OSS.
This article examines the Aurora MySQL MCP Server, which was officially released by AWS.
I hope this helps in some way.
awslabs AWS MCP ServersAmazon Aurora MySQL MCP ServerCreating a verification tableSet up MCP with Cursor and execute queries in natural languageAutomatically aggregate slow logs and get suggestions for improvementsAbout RiskConclusion
awslabs AWS MCP Servers
The official AWS MCP server group can be found here.
When it was first released, there were only a few varieties, but when I looked recently, I saw that there were a lot more varieties.
Here are just a few of the most recent releases that caught my eye.
Amazon Aurora MySQL MCP Server
I'm particularly concernedAmazon Aurora MySQL MCP ServerWe tried to verify the following.
The documentation for the information you need to get started can be found here.
Here are some features from the above document:
Features Natural language to MySQL SQL query Converting human-readable questions and commands into structured MySQL-compatible SQL queries and executing them against the configured Aurora MySQL database.
function
Natural Language to MySQL SQL Query Translation: Translates human-readable questions and commands into structured, MySQL-compatible SQL queries and executes them against your configured Aurora MySQL database.
RDS Data APIRDS Data API usage restrictions
- Not available for burstable instance classes (t3, t4)
- Aurora MySQL version 3.07 or later required
It is important to note that there is a
To enable the RDS Data API on an existing cluster that meets the above requirements:
Scroll to the bottom of the "Connection and Security" tab of the existing cluster and change the settings that appear.
Click Enable RDS Data API.
Creating a verification table
Connect to Aurora MySQL and create two tables for verification.
Insert several dozen pieces of appropriate data into each table.
Sample INSERT Statement
Set up MCP with Cursor and execute queries in natural language
Here we show an example using Cursor as an MCP setting.
Create .cursor/mcp.json in the directory you are working in.
Give instructions in the cursor chat box.
You will then be asked for permission to start the docker defined in mcp.json, so press "Run".
テーブル一覧を取得してください
SHOW TABLE;
Currently, if the query suggested above has a ; at the end, an error will occur.
This seems to be an error in the implementation of mysql-mcp-server.
; ;
You can also check the structure of a specific table.
Automatically aggregate slow logs and get suggestions for improvements
The slow logs will be automatically compiled and suggestions for improvement such as adding an index will be made.
First, as instructed, they performed the aggregation using mysqldumpslow.
From here, the system will automatically check the actual table situation using the MCP.
*In the sample query, only a few dozen records were inserted, but to make it a slow query, millions of records were added.
The analysis results were displayed as follows:
They also provide information on recommended indexes.
Finally, it also lists some points to be aware of when adding an index.
About Risk
Being able to execute queries in natural language is extremely convenient. In this example, the MCP server is running in read-only mode, allowing only read queries, so I think it's unlikely that any major issues will occur.
However, it is necessary to configure the MCP server for each user's environment, and there may be cases where the server is started without the read-only setting.
As a countermeasure, it may be necessary to limit the DB user information used on the MCP server to those with appropriate permissions.
Also, although this time we are only using it in a verification environment, if you use it in a production environment, it is recommended that you appropriately limit the permissions of the IAM user used by the MCP server.
Conclusion
I found that just using Amazon Aurora MySQL MCP Server seems very useful.
This time, I manually fed the slow query log to the system for analysis, but my hopes are high that if I combine it with Amazon Cloudwatch Logs MCP Server, I might be able to consistently perform everything from log acquisition to query analysis in natural language!
We encourage everyone to try out various official AWS Labs MCP servers.
SRG is looking for people to work with us.
If you're interested, please contact us here.