AI agents use follow_request_reject to create or update resources in Mastodon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mastodon environment.
This tool modifies account relationship state by rejecting a pending follow request. It is reversible (the user could accept or re-request follow), has no destructive effects, and affects only social graph metadata. While it involves account management, the action is a standard, low-impact social feature. Severity is low because rejection of follow requests has minimal blast radius and is easily undone.
From the tool's definition Tool name 'follow_request_reject' and description 'Reject a follow request' indicate modification of follow request state from pending to rejected, a reversible action.
Attacks that exploit this kind of access
Reject a follow request. It is categorised as a Write tool in the Mastodon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mastodon MCP server in PolicyLayer and add a rule for follow_request_reject: 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 Mastodon. Nothing to install.
follow_request_reject 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 follow_request_reject 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 follow_request_reject. 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.
follow_request_reject is provided by the Mastodon MCP server (vitexsoftware/mastodon-mcp-server). 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 →