AI agents call list_direct_messages to retrieve information from Groupme without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries existing direct message data with no capability to modify, delete, or execute operations. It is a straightforward read operation on message history. The blast radius of misuse is low—an AI agent could retrieve messages it shouldn't access, but cannot alter or destroy data, trigger external actions, or move money.
From the tool's definition Tool name 'list_direct_messages' and description 'List direct messages with another user' indicate retrieval of message history without modification, deletion, or side effects.
Attacks that exploit this kind of access
List direct messages with another user. It is categorised as a Read tool in the Groupme MCP Server, which means it retrieves data without modifying state.
Register the Groupme MCP server in PolicyLayer and add a rule for list_direct_messages: 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 Groupme. Nothing to install.
list_direct_messages 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 list_direct_messages 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 list_direct_messages. 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.
list_direct_messages is provided by the Groupme MCP server (kalebjs/groupme-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 →