AI agents use code_edit to create or update resources in Kali-Mcp-Toolkit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kali-Mcp-Toolkit environment.
This tool creates or modifies file content reversibly through search/replace operations. While not destructive (files are not deleted), and not read-only, the ability to edit files in a security toolkit context where code execution is adjacent poses risk if an AI agent makes unintended edits.
From the tool's definition The tool description states it can "Edit an existing file using search/replace patches." This performs reversible modification of existing data, which is the core definition of Write.
Documented attack patterns abuse exactly the kind of access code_edit gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kali-Mcp-Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for code_edit:
{
"version": "1",
"default": "deny",
"tools": {
"code_edit": {
"limits": [
{
"counter": "code_edit_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}code_edit 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.
Edit an existing file using search/replace patches. It is categorised as a Write tool in the Kali-Mcp-Toolkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kali-Mcp-Toolkit MCP server in PolicyLayer and add a rule for code_edit: 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-Toolkit. Nothing to install.
code_edit 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 code_edit 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 code_edit. 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.
code_edit is provided by the Kali-Mcp-Toolkit MCP server (trymonoly/kali-mcp-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kali-Mcp-Toolkit, 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.
20 Kali-Mcp-Toolkit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.