executes sql query on DuckDB in-memory database for querying cached Tally Prime report data in table generated as output by other tools (in tableID property from tool output response). These tables are temporary and will be dropped after 15 minutes automatically. Use this tool to run complex anal...
AI agents invoke query-database to trigger actions in Tally Prime 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 executes arbitrary SQL queries against a DuckDB in-memory database. While the description states it queries 'cached Tally Prime report data' (suggesting read-only intent), the tool accepts arbitrary SQL which could include destructive statements (DROP, DELETE) or other unintended operations. The execution of arbitrary SQL on a financial ERP-linked database represents a high severity risk.
From the tool's definition 'executes sql query on DuckDB in-memory database' and 'run complex analytical queries to aggregate, filter, sort results'
Attacks that exploit this kind of access
executes sql query on DuckDB in-memory database for querying cached Tally Prime report data in table generated as output by other tools (in tableID property from tool output response). These tables are temporary and will be dropped after 15 minutes automatically. Use this tool to run complex analytical queries to aggregate, filter, sort results. Returns output in tab separated format. It is categorised as a Execute tool in the Tally Prime MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tally Prime MCP Server MCP server in PolicyLayer and add a rule for query-database: 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.
query-database 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 query-database 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 query-database. 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.
query-database is provided by the Tally Prime MCP Server MCP server (jina-code-systems/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 →