AI agents call account_get 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 account data without modifying, deleting, or executing operations. It is a simple lookup that returns publicly or privately accessible account information. The blast radius of misuse is minimal—an AI agent could retrieve information about accounts, but cannot cause lasting damage or perform irreversible actions.
From the tool's definition Tool name 'account_get' and description 'Get a Mastodon account by its numeric ID' indicate retrieval of account information. The verb 'get' and the action of fetching data by ID are characteristic of read-only operations with no side effects.
Attacks that exploit this kind of access
Get a Mastodon account by its numeric ID. 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_get: 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_get 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_get 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_get. 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_get 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 →