Save content to a timestamped file for evidence collection
AI agents use save_output to create or update resources in Kali MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kali MCP Server environment.
This tool writes data to the filesystem by creating timestamped files. While file creation is reversible (files can be deleted), the medium severity reflects that an AI agent could write sensitive data, evidence files, or logs to unintended locations, consume disk space, or create audit trail artifacts that persist.
From the tool's definition Tool name 'save_output' and description 'Save content to a timestamped file for evidence collection' indicate file creation/writing functionality. It creates new timestamped files but does not irreversibly delete data.
Documented attack patterns abuse exactly the kind of access save_output gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kali MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for save_output:
{
"version": "1",
"default": "deny",
"tools": {
"save_output": {
"limits": [
{
"counter": "save_output_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_output stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Save content to a timestamped file for evidence collection. It is categorised as a Write tool in the Kali MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kali MCP Server MCP server in PolicyLayer and add a rule for save_output: 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 Kali MCP Server. Nothing to install.
save_output 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 save_output 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 save_output. 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.
save_output is provided by the Kali MCP Server MCP server (k3nn3dy-ai/kali-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kali MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
36 Kali MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.