AI agents use xml_format 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 |
|---|---|---|---|
input | string | Yes | XML string |
action | string | — | Action (default: beautify) |
Parameters from the server's own tool schema.
XML formatting is a write operation: it creates a modified (reformatted) version of input XML. However, severity is low because: (1) the operation is entirely reversible (original can be recovered), (2) no data is created, deleted, or permanently changed, (3) no external systems are affected, and (4) misuse by an AI agent poses minimal risk—worst case is incorrectly formatted XML that can be easily regenerated.
From the tool's definition Tool performs 'Beautify or minify XML code' — a reversible formatting operation that modifies the structural representation of XML without changing underlying data or logic.
Attacks that exploit this kind of access
Beautify or minify XML code. 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.
xml_format accepts 2 parameters: input, action. Required: input. 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 xml_format: 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.
xml_format 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 xml_format 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 xml_format. 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.
xml_format 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 →