AI agents invoke write_query to trigger actions in StarRocks MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool name 'write_query' strongly suggests it executes SQL queries that modify data (INSERT, UPDATE, DELETE, DDL). The server's purpose is 'direct SQL execution', and the sibling tool 'read_query' implies a read/write distinction. Since write SQL can include destructive operations (DROP, DELETE) but the name implies general write operations, Execute is the most appropriate category.
From the tool's definition Tool name 'write_query' on a server described as enabling 'direct SQL execution'; sibling tools include 'read_query', implying this tool handles write/mutating SQL statements.
Documented attack patterns abuse exactly the kind of access write_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and StarRocks MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for write_query:
{
"version": "1",
"default": "deny",
"tools": {
"write_query": {
"limits": [
{
"counter": "write_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}write_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
write_query. It is categorised as a Execute tool in the StarRocks MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the StarRocks MCP Server MCP server in PolicyLayer and add a rule for write_query: 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 StarRocks MCP Server. Nothing to install.
write_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the write_query 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 write_query. 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.
write_query is provided by the StarRocks MCP Server MCP server (starrocks/mcp-server-starrocks). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 StarRocks MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 StarRocks MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.