AI agents use account_update 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.
account_update modifies account settings or properties reversibly (typical Mastodon account updates include profile info, privacy settings, etc.), making it Write category. Severity is medium because an AI agent could change account settings maliciously (e.g., alter profile, disable notifications, change credentials) but these are typically reversible and do not permanently destroy data or move money.
From the tool's definition Tool name 'account_update' on a Mastodon server with description stating it enables 'manage accounts'. The sibling tools (account_follow, account_mute, account_block, account_unblock) confirm this server modifies account state.
Attacks that exploit this kind of access
account_update. 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 account_update: 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_update 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 account_update 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_update. 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_update 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 →