find_contact
AI agents call find_contact to retrieve information from Bluebubbles without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
'find_contact' retrieves contact information—a non-destructive query operation with no side effects. Even though the tool description is empty, the name clearly indicates a search/lookup function, which falls under the Read category. The severity is low because contact lookups retrieve information without modifying state or enabling harmful actions directly.
From the tool's definition Tool name is 'find_contact' and exists alongside other tools like 'check_imessage', 'create_chat', and 'download_attachment' in a BlueBubbles iMessage interaction server.
Attacks that exploit this kind of access
find_contact. It is categorised as a Read tool in the Bluebubbles MCP Server, which means it retrieves data without modifying state.
Register the Bluebubbles MCP server in PolicyLayer and add a rule for find_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 Bluebubbles. Nothing to install.
find_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 find_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 find_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.
find_contact is provided by the Bluebubbles MCP server (metaember/bluebubbles-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 →