AI agents use create_bot 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.
Creating a bot is a write operation that generates a new resource reversibly. It modifies the state of the GroupMe platform by adding a new bot, but the action can be undone (via 'destroy_bot' which appears as a sibling tool). This is not destructive because the bot can be deleted, not execute because it does not run arbitrary code or commands, and not financial.
From the tool's definition Tool name 'create_bot' combined with server context indicating GroupMe bot management capabilities. Server description explicitly states it 'allow[s] AI assistants to manage groups, messages, members, and bots.' The tool name and server description together…
Attacks that exploit this kind of access
create_bot. 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_bot: 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_bot 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_bot 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_bot. 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_bot 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 →