AI agents call mastodon_search to retrieve information from Mastodon MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from Mastodon without creating, modifying, deleting, or executing any actions. It is a standard read/search operation analogous to GET requests. The lack of any argument-dependent side effects or destructive capability places it firmly in the Read category with low severity.
From the tool's definition Tool performs 'Search for accounts, hashtags, or posts on Mastodon' — a query operation with no modification, deletion, or side effects.
Documented attack patterns abuse exactly the kind of access mastodon_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mastodon MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for mastodon_search:
{
"version": "1",
"default": "deny",
"tools": {
"mastodon_search": {}
}
}mastodon_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for accounts, hashtags, or posts on Mastodon. It is categorised as a Read tool in the Mastodon MCP MCP Server, which means it retrieves data without modifying state.
Register the Mastodon MCP server in PolicyLayer and add a rule for mastodon_search: 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 MCP. Nothing to install.
mastodon_search 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 mastodon_search 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 mastodon_search. 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.
mastodon_search is provided by the Mastodon MCP server (the-focus-ai/mastodon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mastodon MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Mastodon MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.