AI agents use fill_and_save to create or update resources in Report — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Report environment.
The tool modifies existing templates by populating them with content and persists those changes to disk via file save operations. This is reversible (files can be edited or deleted afterward), so it is Write rather than Destructive. While the description for this specific tool is empty, the server description and tool name provide sufficient context.
From the tool's definition Tool name 'fill_and_save' combined with server description stating it 'filling uploaded document templates' and 'saving as files' indicates the tool creates or modifies document files.
Attacks that exploit this kind of access
fill_and_save. It is categorised as a Write tool in the Report MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Report MCP server in PolicyLayer and add a rule for fill_and_save: 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 Report. Nothing to install.
fill_and_save 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 fill_and_save 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 fill_and_save. 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.
fill_and_save is provided by the Report MCP server (jaykim429/report-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 →