PREFERRED for financial data retrieval. Returns a trial balance pivoted by account group — one row per account group with amounts summed across all accounts in that group, for each requested period. All data is returned in a single response with NO pagination. Use this tool whenever the user asks...
AI agents call pivot_trial_balance_by_account_group to retrieve information from TreeBeam MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries financial accounting data (trial balance) without creating, modifying, deleting, or executing any operations. It performs aggregation and pivoting on existing data for reporting purposes. While it accesses financial data, the tool itself does not move money, create financial obligations, or perform any destructive or executable actions.
From the tool's definition Tool returns a trial balance pivoted by account group with amounts summed across accounts. The description explicitly states it is 'PREFERRED for financial data retrieval' and returns data 'with NO pagination' in a single response.
Attacks that exploit this kind of access
PREFERRED for financial data retrieval. Returns a trial balance pivoted by account group — one row per account group with amounts summed across all accounts in that group, for each requested period. All data is returned in a single response with NO pagination. Use this tool whenever the user asks about balances or totals grouped by account group (e.g. It is categorised as a Read tool in the TreeBeam MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TreeBeam MCP Server MCP server in PolicyLayer and add a rule for pivot_trial_balance_by_account_group: 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 TreeBeam MCP Server. Nothing to install.
pivot_trial_balance_by_account_group 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 pivot_trial_balance_by_account_group 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 pivot_trial_balance_by_account_group. 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.
pivot_trial_balance_by_account_group is provided by the TreeBeam MCP Server MCP server (treebeam-code/tb-mcpserver). 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 →