whatsapp_send_message
Sends a text message to a WhatsApp chat. The chat_id MUST come from a previous whatsapp_list_chats call — never fabricate IDs. This is a write operation: the first call (confirm=false) returns a preview without sending; set confirm=true to actually send. ⚠️ Uses Wacli (unofficial WhatsApp client)...
This record as markdown: /tools/com-local-mcp-local-mcp/whatsapp-send-message.md
What whatsapp_send_message does on Local
AI agents use whatsapp_send_message to create or update resources in Local, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Local environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | Plain-text message body |
chat_id | string | Yes | Chat ID from whatsapp_list_chats |
confirm | boolean | — | Must be true to actually send. Without it, returns a preview. |
Parameters from the server's own tool schema.
Why whatsapp_send_message is rated Medium
This tool creates new data (messages) in WhatsApp chats, which is a reversible write operation. While messages can theoretically be deleted after sending, the primary effect is creation/modification of chat state. It does not execute arbitrary code, delete data irreversibly, or move money, so Write is the appropriate category.
From the tool's definition Tool description explicitly states 'Sends a text message to a WhatsApp chat' and 'This is a write operation: the first call (confirm=false) returns a preview without sending; set confirm=true to actually send.' The tool modifies state by creating new messages…
Attacks that exploit this kind of access
The rule that runs whatsapp_send_message safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For whatsapp_send_message, this is the rule to start with:
whatsapp_send_message stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every whatsapp_send_message call is checked against it from then on.
Questions about whatsapp_send_message
Sends a text message to a WhatsApp chat. The chat_id MUST come from a previous whatsapp_list_chats call — never fabricate IDs. This is a write operation: the first call (confirm=false) returns a preview without sending; set confirm=true to actually send. ⚠️ Uses Wacli (unofficial WhatsApp client). Accounts may be restricted for ToS violations. It is categorised as a Write tool in the Local MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
whatsapp_send_message accepts 3 parameters: text, chat_id, confirm. Required: text, chat_id. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for whatsapp_send_message: 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 Local. Nothing to install.
whatsapp_send_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the whatsapp_send_message 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 whatsapp_send_message. 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.
whatsapp_send_message is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
This server
Across the catalogue