AI agents call bookmarks 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 existing bookmark data for the authenticated user. It queries and returns information without modifying, creating, deleting, or executing any operations. The 'Get' verb and read-only nature of accessing one's own bookmarks clearly place it in the Read category with low severity, as the blast radius of misuse is limited to viewing already-bookmarked content.
From the tool's definition Tool name 'bookmarks' and description 'Get statuses bookmarked by the authenticated account' indicates a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get statuses bookmarked by the authenticated 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 bookmarks: 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.
bookmarks 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 bookmarks 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 bookmarks. 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.
bookmarks 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 →