AI agents call get_session_qr to retrieve information from Chatkazi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only fetches display data (a QR code image/link) needed for user authentication pairing. It does not modify sessions, send messages, execute commands, or trigger external side effects. While the QR code facilitates WhatsApp connection setup, the tool itself performs no destructive or irreversible action—it is purely informational retrieval.
From the tool's definition Tool retrieves a QR code pairing link for an initialized session—a data query operation with no state modification. The description explicitly states 'Retrieve', indicating a read-only action.
Attacks that exploit this kind of access
Retrieve the QR code pairing link for an initialized session. It is categorised as a Read tool in the Chatkazi MCP Server, which means it retrieves data without modifying state.
Register the Chatkazi MCP server in PolicyLayer and add a rule for get_session_qr: 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 Chatkazi. Nothing to install.
get_session_qr 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_session_qr 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_session_qr. 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_session_qr is provided by the Chatkazi MCP server (lxmwaniky/chatkazi-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 →