Read output from an interactive session without sending new commands.
AI agents call interactive_read to retrieve information from K-MCP: Kali Model Context Protocol Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and reads output from an existing interactive session, which is a read operation with no side effects. However, severity is medium rather than low because the context (Kali Linux, penetration testing, security tools) means the data being read could be sensitive reconnaissance information, credentials, or results from active attacks that could inform malicious follow-up actions.
From the tool's definition Tool name 'interactive_read' combined with description 'Read output from an interactive session without sending new commands' explicitly indicates retrieval of data from session output without execution or modification.
Attacks that exploit this kind of access
Read output from an interactive session without sending new commands. It is categorised as a Read tool in the K-MCP: Kali Model Context Protocol Server MCP Server, which means it retrieves data without modifying state.
Register the K-MCP: Kali Model Context Protocol Server MCP server in PolicyLayer and add a rule for interactive_read: 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 K-MCP: Kali Model Context Protocol Server. Nothing to install.
interactive_read 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 interactive_read 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 interactive_read. 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.
interactive_read is provided by the K-MCP: Kali Model Context Protocol Server MCP server (stoicmehedi/k-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 →