Begin a TOM write transaction. While open, model write tools (create_measure, delete_measure, batch_update_measures) defer saving until tom_commit_transaction, so a batch of edits is atomic and can be rolled back.
AI agents invoke tom_begin_transaction to trigger actions in Power BI 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.
This tool initiates a write transaction context in the Tabular Object Model (TOM). It doesn't directly read, write, or destroy data itself, but it triggers an external operation that gates and coordinates subsequent write/destructive actions. Since it enables atomic batched writes including deletions (delete_measure) and is a prerequisite for those operations, it functions as a transaction control mechanism.
From the tool's definition Begin a TOM write transaction... model write tools defer saving until tom_commit_transaction, so a batch of edits is atomic and can be rolled back
Attacks that exploit this kind of access
Begin a TOM write transaction. While open, model write tools (create_measure, delete_measure, batch_update_measures) defer saving until tom_commit_transaction, so a batch of edits is atomic and can be rolled back. It is categorised as a Execute tool in the Power BI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Power BI MCP Server MCP server in PolicyLayer and add a rule for tom_begin_transaction: 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 Power BI MCP Server. Nothing to install.
tom_begin_transaction 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 tom_begin_transaction 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 tom_begin_transaction. 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.
tom_begin_transaction is provided by the Power BI MCP Server MCP server (sulaiman013/powerbi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.