AI agents use file_generate to create or update resources in Tools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tools environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
data | array | Yes | Array of objects to generate file from |
format | string | Yes | Output format (default: csv) |
options | object | — |
Parameters from the server's own tool schema.
This tool creates new files programmatically, which is a Write operation. Severity is medium because while file generation is reversible and the blast radius is limited to file creation, an AI agent could generate numerous files, consume storage resources, or create files with malicious content for later use.
From the tool's definition Tool generates and returns files in CSV/TSV/JSON formats from structured data. The description explicitly states 'Generate... file' and 'Returns base64-encoded file and raw text', indicating file creation.
Attacks that exploit this kind of access
Generate CSV/TSV/JSON file from structured data array. Returns base64-encoded file and raw text. It is categorised as a Write tool in the Tools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
file_generate accepts 3 parameters: data, format, options. Required: data, format. The full parameter table on this page comes from the server's own tool schema.
Register the Tools MCP server in PolicyLayer and add a rule for file_generate: 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 Tools. Nothing to install.
file_generate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the file_generate 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 file_generate. 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.
file_generate is provided by the Tools MCP server (https://www.jiebang.site/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 →