AI agents use repost to create or update resources in Bluesky — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bluesky environment.
Reposts create new social media engagements on behalf of the user. While reversible via 'unrepost' (evident from sibling tools), they modify account state and can amplify content without user review per interaction. This is a Write action—data creation/modification without irreversibility or code execution.
From the tool's definition Tool name 'repost' combined with description 'Repost someone' indicates creating/sharing content. Sibling tools include 'create-post', 'delete-post', 'like-post', confirming this server modifies social media state.
Documented attack patterns abuse exactly the kind of access repost gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bluesky, and nothing reaches the server without passing your rules. This is the rule we recommend for repost:
{
"version": "1",
"default": "deny",
"tools": {
"repost": {
"limits": [
{
"counter": "repost_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}repost 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.
Repost someone. It is categorised as a Write tool in the Bluesky MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bluesky MCP server in PolicyLayer and add a rule for repost: 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 Bluesky. Nothing to install.
repost 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 repost 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 repost. 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.
repost is provided by the Bluesky MCP server (semioz/bluesky-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bluesky, 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.
11 Bluesky tools catalogued and risk-classified — across an index of 43,000+ MCP servers.