This record as markdown: /tools/seac-25-kali-security-mcp/extract-endpoints.md
What extract_endpoints does on Kali Security MCP
AI agents call extract_endpoints to retrieve information from Kali Security MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why extract_endpoints is rated Low
The tool performs data extraction and analysis without modifying, executing, or deleting anything. It reads response content to identify and catalog endpoints and API paths — a reconnaissance activity with no side effects. Given the Kali security context, this is part of a penetration testing workflow where endpoint discovery is a preliminary Read-phase activity.
From the tool's definition Tool description states 'extract_endpoints' — 从响应中提取端点和API路径 (extract endpoints and API paths from responses). This is a parsing/extraction operation on existing response data.
Attacks that exploit this kind of access
The rule that runs extract_endpoints safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Kali Security MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For extract_endpoints, this is the rule to start with:
extract_endpoints is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Kali Security MCP, apply this rule, and every extract_endpoints call is checked against it from then on.
Questions about extract_endpoints
从响应中提取端点和API路径. It is categorised as a Read tool in the Kali Security MCP MCP Server, which means it retrieves data without modifying state.
Register the Kali Security MCP server in PolicyLayer and add a rule for extract_endpoints: 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 Security MCP. Nothing to install.
extract_endpoints 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 extract_endpoints 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 extract_endpoints. 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.
extract_endpoints is provided by the Kali Security MCP server (seac-25/kali-security-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Kali Security, and thousands of servers like it.
This server
Across the catalogue