fetches trial balance with fields ledger_name, group_name (blank if Profit & Loss), opening_balance, net_debit, net_credit, closing_balance. opening_balance and closing_balance negative is debit and positive is credit. kindly fetch data from chart-of-accounts tool to pull group hierarchy before c...
AI agents call trial-balance to retrieve information from Tally Prime MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves financial report data (trial balance) from Tally Prime ERP and caches it in an in-memory table for querying. It performs no writes, deletions, or financial transactions — it is purely a read/fetch operation. The in-memory caching is ephemeral and non-destructive. Severity is low as misuse only exposes financial report data without any side effects.
From the tool's definition fetches trial balance with fields ledger_name, group_name, opening_balance, net_debit, net_credit, closing_balance... returns output cached in pglite postgres in-memory table
Attacks that exploit this kind of access
fetches trial balance with fields ledger_name, group_name (blank if Profit & Loss), opening_balance, net_debit, net_credit, closing_balance. opening_balance and closing_balance negative is debit and positive is credit. kindly fetch data from chart-of-accounts tool to pull group hierarchy before calling this tool. returns output cached in pglite postgres in-memory table (specified in tableID property). Use query-database tool to run SQL queries against that table for further analysis. It is categorised as a Read tool in the Tally Prime MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tally Prime MCP Server MCP server in PolicyLayer and add a rule for trial-balance: 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 Tally Prime MCP Server. Nothing to install.
trial-balance 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 trial-balance 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 trial-balance. 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.
trial-balance is provided by the Tally Prime MCP Server MCP server (qalalabs/tally-mcp-server). 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 →