AI agents invoke start_session to trigger actions in Chatkazi. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
While 'start_session' itself does not send messages or delete data, it triggers external operations (WhatsApp session establishment) that are conditional on subsequent actions.
From the tool's definition Tool 'start_session' initializes a new WhatsApp session connection. Combined with sibling tools like 'send_whatsapp_text' and 'send_whatsapp_media', this enables execution of external messaging operations whose effects depend on how the session is…
Attacks that exploit this kind of access
Initialize a new WhatsApp session connection. It is categorised as a Execute tool in the Chatkazi MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chatkazi MCP server in PolicyLayer and add a rule for start_session: 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.
start_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_session 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 start_session. 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.
start_session 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 →