AI agents use write_query to create or update resources in MSSQL MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MSSQL MCP Server environment.
The tool performs data modification (INSERT, UPDATE, DELETE) on a database. While DELETE technically modifies data irreversibly at the statement level, the description groups it with INSERT/UPDATE, suggesting the tool's primary classification is Write rather than Destructive. However, if the tool permits DELETE without transaction wrapping or recovery mechanisms, the severity is high due to potential data loss.
From the tool's definition Tool description explicitly states it 'Execute an INSERT, UPDATE, or DELETE query'. INSERT and UPDATE are reversible write operations; DELETE is reversible in context of transaction rollback but is inherently a write action.
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 MSSQL 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": 30,
"scope": "grant"
}
]
}
}
}write_query 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.
Execute an INSERT, UPDATE, or DELETE query. It is categorised as a Write tool in the MSSQL MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MSSQL 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 MSSQL MCP Server. Nothing to install.
write_query 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 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 MSSQL MCP Server MCP server (jensenloke/mcp-sqlserver-pro). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MSSQL 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.
23 MSSQL MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.