AI agents call get_contact to retrieve information from Whatsapp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves contact and group metadata (name, participants, admin status) without modifying, deleting, or executing any operations. It is a pure data query operation consistent with the read-only nature of the server. Severity is low because contact information exposure has limited blast radius in typical scenarios.
From the tool's definition Tool description states 'Get contact or group info by chat_id' with fields like 'subject, participants, admins'. The server is explicitly described as 'read-only interface to WhatsApp'. No mutation, deletion, or execution capabilities are present.
Attacks that exploit this kind of access
Get contact or group info by chat_id. Polymorphic: returns direct-contact fields for @c.us IDs, group fields (subject, participants, admins) for @g.us IDs. It is categorised as a Read tool in the Whatsapp MCP Server, which means it retrieves data without modifying state.
Register the Whatsapp MCP server in PolicyLayer and add a rule for get_contact: 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. Nothing to install.
get_contact 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_contact 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_contact. 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_contact is provided by the Whatsapp MCP server (joaohts/whatsapp-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 →