AI agents use convert_format to create or update resources in Struct — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Struct environment.
The tool performs a format conversion operation, which is a data transformation that creates a modified version of existing data. This is a Write-class operation because it produces new output/data structure, but not Destructive since the conversion itself doesn't permanently delete or overwrite the original source data.
From the tool's definition Tool name 'convert_format' and description 'Convert structure to different format' indicate the tool modifies or transforms data from one representation to another without irreversibly deleting the original.
Attacks that exploit this kind of access
Convert structure to different format. It is categorised as a Write tool in the Struct MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Struct MCP server in PolicyLayer and add a rule for convert_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 Struct. Nothing to install.
convert_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 convert_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 convert_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.
convert_format is provided by the Struct MCP server (laurears/struct-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 →