Count the number of rows matching given filters
AI agents call count_rows to retrieve information from Omics AI 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 aggregate information (row counts) from a dataset based on filter criteria. It is a safe, non-destructive query operation with no side effects. The ability to count rows with filters is a standard read operation that does not alter data or trigger external operations. Severity is low because even with misuse, an agent can only enumerate dataset sizes, posing minimal risk.
From the tool's definition Tool name 'count_rows' and description 'Count the number of rows matching given filters' indicate a read-only aggregation query. No modification, deletion, or execution of arbitrary code is implied.
Attacks that exploit this kind of access
Count the number of rows matching given filters. It is categorised as a Read tool in the Omics AI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Omics AI MCP Server MCP server in PolicyLayer and add a rule for count_rows: 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 Omics AI MCP Server. Nothing to install.
count_rows 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 count_rows 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 count_rows. 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.
count_rows is provided by the Omics AI MCP Server MCP server (mfiume/omics-ai-mcp). 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 →