AI agents call account_following 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 is a straightforward read operation that queries and returns a list of accounts followed by a specified account. It performs no modifications, deletions, or external actions. The retrieval of social graph information (followers/following relationships) is a standard Read category operation.
From the tool's definition Tool is named 'account_following' and described as 'Get accounts that a given account follows' — this retrieves/queries account relationship data with no modification or side effects.
Attacks that exploit this kind of access
Get accounts that a given account follows. 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_following: 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_following 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_following 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_following. 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_following 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 →