AI agents call account_followers to retrieve information from Mastodon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publicly available follower information from a Mastodon account. No data is created, modified, deleted, or any external operations are triggered. It is a simple information lookup with no mutations or irreversible effects. The low severity reflects that misuse would only expose already-public social information.
From the tool's definition Tool name 'account_followers' and description 'Get followers of an account' indicate a retrieval operation with no side effects. The verb 'Get' explicitly denotes a read-only query.
Attacks that exploit this kind of access
Get followers of an account. It is categorised as a Read tool in the Mastodon MCP Server, which means it retrieves data without modifying state.
Register the Mastodon MCP server in PolicyLayer and add a rule for account_followers: 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.
account_followers 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 account_followers 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 account_followers. 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.
account_followers 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 →