delete_function

THE RISK

Critical Risk

Why delete_function needs a policy

This tool irreversibly deletes analysis artifacts (function definitions) from a Ghidra binary analysis project. Once a function definition is removed, recovering that analytical work requires re-analysis. This is a destructive operation that cannot be undone through normal means, placing it in the Destructive category rather than Write.

From the tool's definition Tool explicitly performs 'Delete a function' operation. The description states it 'Removes the function definition' - this is an irreversible modification to the analysis database/project state.

Documented attack patterns abuse exactly the kind of access delete_function gives an agent:

POLICY

How to control delete_function

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 delete_function:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_function"
  ]
}

delete_function disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Kawaiidra MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Kawaiidra MCP tools

Destructive cache_clear Clear cached analysis results. Can clear all cache or filter by binary/project. Destructive clear_comments Clear all comments (EOL, PRE, POST, PLATE) within a function Destructive delete_data_type Delete a user-defined data type from the binary. Destructive delete_label Delete a label/symbol at a specific address. Destructive remove_struct_field Remove a field from a structure by index. Execute run_script Execute arbitrary Jython code in the Ghidra scripting environment. Has access to currentPr Execute analyze_binary Import and analyze a binary file with Ghidra. Supports PE, ELF, Mach-O, and raw formats. Write add_enum_value Add a value to an existing enumeration.

All 94 Kawaiidra MCP tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Kawaiidra MCP → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about delete_function

What does the delete_function tool do? +

Delete a function by address or name. Removes the function definition but not the underlying code bytes. It is categorised as a Destructive tool in the Kawaiidra MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_function? +

Register the Kawaiidra MCP server in PolicyLayer and add a rule for delete_function: 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.

What risk level is delete_function? +

delete_function is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_function? +

Yes. Add a rate_limit block to the delete_function 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.

How do I block delete_function completely? +

Set action: deny in the PolicyLayer policy for delete_function. 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.

What MCP server provides delete_function? +

delete_function 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.

Enforce policy on every Kawaiidra MCP tool call.

Start from Kawaiidra MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →