Validate KQL query syntax
AI agents call validate_query to retrieve information from Azure Log Analytics MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only checks whether a query conforms to KQL syntax rules. It does not retrieve data (Read would be checking actual logs), execute queries against live data (Execute), modify workspace configuration (Write), delete anything (Destructive), or involve financial transactions (Financial). While it operates in the context of a querying system, the specific action is purely analytical and non-invasive.
From the tool's definition The tool performs syntax validation of KQL queries without executing them or modifying any data. The description states 'Validate KQL query syntax' with no mention of execution, modification, or deletion.
Attacks that exploit this kind of access
Validate KQL query syntax. It is categorised as a Read tool in the Azure Log Analytics MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Azure Log Analytics MCP Server MCP server in PolicyLayer and add a rule for validate_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 Azure Log Analytics MCP Server. Nothing to install.
validate_query is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the validate_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 validate_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.
validate_query is provided by the Azure Log Analytics MCP Server MCP server (rasta26/azure_log_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →