AI agents use mastodon_unfollow to create or update resources in Crow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Crow environment.
Unfollowing an account modifies social graph state (removes a follow relationship) on Mastodon. This is a reversible write action (you can re-follow), not destructive. Misuse by an AI agent could silently sever social connections, warranting medium severity.
From the tool's definition 'Unfollow an account' — removes a following relationship
Documented attack patterns abuse exactly the kind of access mastodon_unfollow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for mastodon_unfollow:
{
"version": "1",
"default": "deny",
"tools": {
"mastodon_unfollow": {
"limits": [
{
"counter": "mastodon_unfollow_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} mastodon_unfollow stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Unfollow an account. It is categorised as a Write tool in the Crow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Crow MCP server in PolicyLayer and add a rule for mastodon_unfollow: 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 Crow. Nothing to install.
mastodon_unfollow is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mastodon_unfollow 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_unfollow. 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_unfollow is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, 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.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.