get_query_plan
AI agents call get_query_plan to retrieve information from Fabric Dw Mcp Cli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Query plan retrieval is a non-destructive read operation that does not modify data or execute arbitrary queries. However, query plans may expose schema, indexing strategy, and performance characteristics that could inform malicious attacks; this warrants medium severity. Confidence is reduced because the description is empty and the tool's exact behavior and information exposure scope cannot be fully verified.
From the tool's definition Tool name 'get_query_plan' suggests retrieval of query execution plan information, consistent with sibling Read tools like 'get_audit_settings' and 'count_table_rows'. Description is empty, reducing confidence.
Attacks that exploit this kind of access
get_query_plan. It is categorised as a Read tool in the Fabric Dw Mcp Cli MCP Server, which means it retrieves data without modifying state.
Register the Fabric Dw Mcp Cli MCP server in PolicyLayer and add a rule for get_query_plan: 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 Fabric Dw Mcp Cli. Nothing to install.
get_query_plan 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 get_query_plan 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 get_query_plan. 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.
get_query_plan is provided by the Fabric Dw Mcp Cli MCP server (sdebruyn/fabric-dw-mcp-cli). 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 →