AI agents call trending_links 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 trending links from a Mastodon instance. It performs a read-only query operation that does not create, modify, delete, or execute any actions. The blast radius is minimal—an AI agent cannot misuse this to cause harm, as it only fetches aggregate trending data already public on the instance.
From the tool's definition Tool name 'trending_links' and description 'Get trending links (articles) on the instance' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get trending links (articles) on the instance. 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 trending_links: 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.
trending_links 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 trending_links 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 trending_links. 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.
trending_links 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 →