AI agents invoke open_session to trigger actions in WhatsApp MCP Server. 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.
Opening a session triggers an external operation (authenticating and establishing a connection to WhatsApp/GreenAPI), which is an Execute-level action. It doesn't read existing data, write/modify records, or delete anything, but it does initiate an external process whose effects depend on the account context. Misuse could lead to unauthorized sessions or account linking, hence medium severity.
From the tool's definition 'Open a new WhatsApp session' — initiates an external session/connection to WhatsApp Business API via GreenAPI
Documented attack patterns abuse exactly the kind of access open_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WhatsApp MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for open_session:
{
"version": "1",
"default": "deny",
"tools": {
"open_session": {
"limits": [
{
"counter": "open_session_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}open_session stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Open a new WhatsApp session. It is categorised as a Execute tool in the WhatsApp MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the WhatsApp MCP Server MCP server in PolicyLayer and add a rule for open_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 WhatsApp MCP Server. Nothing to install.
open_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 open_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 open_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.
open_session is provided by the WhatsApp MCP Server MCP server (msaelices/whatsapp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WhatsApp MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 WhatsApp MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.