AI agents use mcp7zop_make_archive to create or update resources in Mcp7zOp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp7zOp environment.
Creating an archive is a write operation that creates new data structures (the archive file itself). While reversible through deletion, the action modifies the file system by writing a new archive. This is less severe than destructive operations (which irreversibly remove data) but more impactful than simple data retrieval.
From the tool's definition Tool name 'mcp7zop_make_archive' combined with server description stating 'archive creation' capability. The tool description is empty, limiting direct evidence.
Attacks that exploit this kind of access
mcp7zop_make_archive. It is categorised as a Write tool in the Mcp7zOp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp7zOp MCP server in PolicyLayer and add a rule for mcp7zop_make_archive: 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 Mcp7zOp. Nothing to install.
mcp7zop_make_archive 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 mcp7zop_make_archive 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 mcp7zop_make_archive. 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.
mcp7zop_make_archive is provided by the Mcp7zOp MCP server (zv-louis/mcp7zop). 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 →