csv_aggregate
Aggregate values from a local CSV (count/sum/avg/min/max) with optional filters. Deterministic, no network.
This record as markdown: /tools/io-github-homenshum-nodebench/csv-aggregate.md
What csv_aggregate does on Nodebench
AI agents call csv_aggregate to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why csv_aggregate is rated Low
csv_aggregate retrieves and computes statistics from existing data without creating, modifying, deleting, or executing external operations. The aggregation functions (count, sum, average, min, max) are analytical queries over local files. No side effects, network calls, or data persistence changes are indicated. This is purely a Read operation with minimal risk.
From the tool's definition Tool performs aggregation operations (count/sum/avg/min/max) on local CSV data with optional filters. Description explicitly states 'Deterministic, no network' and indicates read-only analysis without modification.
Attacks that exploit this kind of access
The rule that runs csv_aggregate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For csv_aggregate, this is the rule to start with:
csv_aggregate is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every csv_aggregate call is checked against it from then on.
Questions about csv_aggregate
Aggregate values from a local CSV (count/sum/avg/min/max) with optional filters. Deterministic, no network. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for csv_aggregate: 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 Nodebench. Nothing to install.
csv_aggregate 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 csv_aggregate 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 csv_aggregate. 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.
csv_aggregate is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue