AI agents use create_group to create or update resources in Groupme — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Groupme environment.
The tool creates a new resource (a group) in the GroupMe platform. This is a Write operation because it results in data creation/modification that is reversible (groups can be deleted via the destroy_group tool noted in sibling tools). The severity is low because creating a group has minimal blast radius—it doesn't delete data, move money, or execute arbitrary code.
From the tool's definition Tool name is 'create_group' and description states 'Create a new group.' This is a reversible creation operation that modifies data by adding a new GroupMe group.
Attacks that exploit this kind of access
Create a new group. It is categorised as a Write tool in the Groupme MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Groupme MCP server in PolicyLayer and add a rule for create_group: 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.
create_group 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 create_group 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 create_group. 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.
create_group 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 →