manage_bluesky_convo
Act on one Bluesky DM conversation. ACCEPT a message request \u2014 Bluesky holds DMs from people the account does not follow in a separate requests folder, and until one is accepted it stays there. MUTE / UNMUTE it. LOCK / UNLOCK it (no new messages). LEAVE it. Or DELETE one message from THIS ac...
This record as markdown: /tools/hermoso/manage-bluesky-convo.md
What manage_bluesky_convo does on Hermoso
AI agents call manage_bluesky_convo to permanently remove resources in Hermoso, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why manage_bluesky_convo is rated Critical
An AI agent that decides to call manage_bluesky_convo doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Hermoso is gone. There is no undo for destructive operations.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs manage_bluesky_convo safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hermoso, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For manage_bluesky_convo, this is the rule to start with:
manage_bluesky_convo is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Hermoso, apply this rule, and every manage_bluesky_convo call is checked against it from then on.
Questions about manage_bluesky_convo
Act on one Bluesky DM conversation. ACCEPT a message request \u2014 Bluesky holds DMs from people the account does not follow in a separate requests folder, and until one is accepted it stays there. MUTE / UNMUTE it. LOCK / UNLOCK it (no new messages). LEAVE it. Or DELETE one message from THIS account\u2019s view. TWO THINGS TO SAY OUT LOUD BEFORE USING THEM: deleting is FOR SELF ONLY \u2014 the other person still sees the message, because Bluesky offers no delete-for-everyone in chat \u2014 and leaving a conversation cannot be undone from here. Accepting a request that was already accepted is reported as such rather than as a change, because Bluesky says so by returning no revision. Free, and it needs the same PRIVILEGED app password as every other Bluesky DM tool. Get a convoId from list_bluesky_convos. It is categorised as a Destructive tool in the Hermoso MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Hermoso MCP server in PolicyLayer and add a rule for manage_bluesky_convo: 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 Hermoso. Nothing to install.
manage_bluesky_convo is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the manage_bluesky_convo 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 manage_bluesky_convo. 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.
manage_bluesky_convo is provided by the Hermoso MCP server (https://app.hermoso.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hermoso, and thousands of servers like it.
Across the catalogue