AI agents use create_label to create or update resources in Kawaiidra MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kawaiidra MCP environment.
This tool creates labels or symbols at addresses within a Ghidra project—a metadata modification operation. While reversible (labels can be deleted or renamed), it modifies the analysis state and could be misused to add misleading labels to confuse or obfuscate the analysis. The impact is scoped to the Ghidra project being analyzed, not production systems, making it Write rather than Execute.
From the tool's definition Tool description: 'Create a label/symbol at a specific address.' The verb 'create' indicates a write operation that adds metadata (labels/symbols) to a binary analysis project. This is a reversible modification.
Documented attack patterns abuse exactly the kind of access create_label gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kawaiidra MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for create_label:
{
"version": "1",
"default": "deny",
"tools": {
"create_label": {
"limits": [
{
"counter": "create_label_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_label 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.
Create a label/symbol at a specific address. It is categorised as a Write tool in the Kawaiidra MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kawaiidra MCP server in PolicyLayer and add a rule for create_label: 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 Kawaiidra MCP. Nothing to install.
create_label 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 create_label 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 create_label. 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.
create_label is provided by the Kawaiidra MCP server (wagonbomb/kawaiidra-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kawaiidra MCP, 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.
94 Kawaiidra MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.