List or search the iMessage/SMS handles the server knows about.
AI agents call query_handles 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.
This tool retrieves contact handle information from the BlueBubbles server without modifying, deleting, or executing any operations. It is purely informational/query-based, analogous to searching a contact list. The verb 'search' and 'list' are explicitly stated read operations with no side effects.
From the tool's definition Tool name 'query_handles' and description states it 'List or search the iMessage/SMS handles' — core read operations with no data modification.
Attacks that exploit this kind of access
List or search the iMessage/SMS handles the server knows about. 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 query_handles: 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.
query_handles 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 query_handles 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 query_handles. 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.
query_handles 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 →