AI agents use update-data to create or update resources in MySQL MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MySQL MCP Server environment.
The tool modifies existing records in a MySQL database, which is a reversible Write operation. It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). Severity is medium because unintended modifications could corrupt important data, but the blast radius is limited to updates rather than irreversible deletions or code execution.
From the tool's definition Tool name is 'update-data' and server description states it enables 'modification...of database tables and records.' The empty tool description is uninformative, but the server-level context clearly indicates this modifies data.
Documented attack patterns abuse exactly the kind of access update-data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MySQL MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update-data:
{
"version": "1",
"default": "deny",
"tools": {
"update-data": {
"limits": [
{
"counter": "update-data_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-data stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
update-data. It is categorised as a Write tool in the MySQL MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MySQL MCP Server MCP server in PolicyLayer and add a rule for update-data: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MySQL MCP Server. Nothing to install.
update-data is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update-data rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update-data. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update-data is provided by the MySQL MCP Server MCP server (log6262635/mcp-mysql). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MySQL MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 MySQL MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.