AI agents use add_files_to_matter_batch to create or update resources in Smokeball — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Smokeball environment.
This tool creates or modifies matter-file associations without deleting or executing arbitrary code. It's a Write operation because it adds data relationships reversibly. Severity is medium because bulk file additions could clutter matters or create compliance/audit issues if misused at scale, but the action is reversible (files can be removed).
From the tool's definition Tool description states 'Add multiple files to a matter' — a write operation that creates associations between files and matters. The batch parameter and CSV format indicate it modifies data structure reversibly.
Attacks that exploit this kind of access
Add multiple files to a matter in one request. files_csv: comma-separated file names. It is categorised as a Write tool in the Smokeball MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Smokeball MCP server in PolicyLayer and add a rule for add_files_to_matter_batch: 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 Smokeball. Nothing to install.
add_files_to_matter_batch 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 add_files_to_matter_batch 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 add_files_to_matter_batch. 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.
add_files_to_matter_batch is provided by the Smokeball MCP server (rosenadvertising/smokeball-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 →