Publish a status (toot). Content is public by default unless visibility is narrowed. Rate-limited: 10/hour per conversation.
AI agents use mastodon_post 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.
This is a Write operation because it creates and publishes new data to an external social media platform. It's elevated to 'high' severity because an AI agent could abuse this tool to spam, impersonate the user, spread misinformation, or damage the user's social reputation through thousands of public posts (the rate limit of 10/hour per conversation can still result in significant harm over time).
From the tool's definition The tool 'mastodon_post' publishes content to a Mastodon instance, which the description explicitly states will be 'public by default.' This creates new data (a status/toot) that is pushed to a social platform and visible to others.
Documented attack patterns abuse exactly the kind of access mastodon_post 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_post:
{
"version": "1",
"default": "deny",
"tools": {
"mastodon_post": {
"limits": [
{
"counter": "mastodon_post_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mastodon_post 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.
Publish a status (toot). Content is public by default unless visibility is narrowed. Rate-limited: 10/hour per conversation. 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_post: 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_post 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_post 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_post. 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_post 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.