get_function_callers
AI agents call get_function_callers to retrieve information from Binary Ninja Cline MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or enumerate static analysis data about function call relationships within a binary, which is a read operation with no side effects. The naming pattern and context (Binary Ninja analysis server) indicate it performs queries on existing binary metadata without modification. Low severity due to information-only nature with limited blast radius.
From the tool's definition Tool name 'get_function_callers' indicates a query/lookup operation that retrieves information about callers of a function.
Attacks that exploit this kind of access
get_function_callers. It is categorised as a Read tool in the Binary Ninja Cline MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Binary Ninja Cline MCP Server MCP server in PolicyLayer and add a rule for get_function_callers: 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 Binary Ninja Cline MCP Server. Nothing to install.
get_function_callers is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_function_callers 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 get_function_callers. 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.
get_function_callers is provided by the Binary Ninja Cline MCP Server MCP server (opensensor/bn_cline_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →