Low Risk

get_code

get_code

How to control get_code ↓

AI agents call get_code to retrieve information from BinAssistMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

The tool is clearly intended to retrieve code (decompiled or disassembled) from a binary analysis context. No side effects, modifications, or execution occurs—it retrieves data for analysis purposes. The empty description slightly reduces confidence from perfect, but the function name and surrounding context of analysis tools strongly indicate a read operation.

From the tool's definition Tool name 'get_code' with context showing it's among read-focused analysis tools like 'analyze_function', 'get_basic_blocks', 'get_binary_info', and 'bookmarks'. The server's purpose is 'analysis' and 'decompilation', which are inherently read operations.

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

PolicyLayer is an MCP gateway — it sits between your AI agents and BinAssistMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_code:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_code": {}
  }
}

get_code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register BinAssistMCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the get_code tool do? +

get_code. It is categorised as a Read tool in the BinAssistMCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_code? +

Register the BinAssist MCP server in PolicyLayer and add a rule for get_code: 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 BinAssistMCP. Nothing to install.

What risk level is get_code? +

get_code is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_code? +

Yes. Add a rate_limit block to the get_code 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 get_code completely? +

Set action: deny in the PolicyLayer policy for get_code. 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 get_code? +

get_code is provided by the BinAssist MCP server (symgraph/binassistmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every BinAssistMCP tool call.

Deterministic rules across all 44 BinAssistMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

44 BinAssistMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.