AI agents call timeline_public 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 available timeline data from a Mastodon instance without modifying, creating, deleting, or executing any code. It has no ability to change state, affect other users, or trigger external operations. The blast radius is minimal—worst case, an AI agent could retrieve large amounts of public data, but this poses no destructive risk to the Mastodon instance or its users.
From the tool's definition Tool name 'timeline_public' and description 'Get the federated public timeline' indicate a retrieval operation with no side effects. The verb 'Get' and the action of fetching a public timeline confirm this is a read-only operation.
Attacks that exploit this kind of access
Get the federated public timeline. 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 timeline_public: 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.
timeline_public 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 timeline_public 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 timeline_public. 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.
timeline_public 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 →