AI agents use create_block 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.
Blocking a user modifies the relationship state and the user's experience (they cannot contact the blocker), but this is reversible via the 'delete_block' tool present on the server. This makes it a Write action rather than Destructive. The severity is medium because blocking can disrupt communication but affects only the interpersonal relationship, not permanent data loss or financial impact.
From the tool's definition Tool name 'create_block' and description 'Block a user' indicate a modification action that creates a blocking relationship between the current user and a target user.
Attacks that exploit this kind of access
Block a user. 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_block: 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_block 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_block 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_block. 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_block 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 →