react_to_bluesky_dm
Add or remove an emoji reaction on one message in a Bluesky DM \u2014 the light acknowledgement that does not need a written reply, and the thing to reach for when someone says \u201cthanks\u201d and a paragraph back would be worse than a thumbs-up. A REACTION IS EXACTLY ONE EMOJI: that is Bluesk...
This record as markdown: /tools/hermoso/react-to-bluesky-dm.md
What react_to_bluesky_dm does on Hermoso
AI agents call react_to_bluesky_dm 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 react_to_bluesky_dm is rated Critical
An AI agent that decides to call react_to_bluesky_dm 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.
Attacks that exploit this kind of access
The rule that runs react_to_bluesky_dm 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 react_to_bluesky_dm, this is the rule to start with:
react_to_bluesky_dm 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 react_to_bluesky_dm call is checked against it from then on.
Questions about react_to_bluesky_dm
Add or remove an emoji reaction on one message in a Bluesky DM \u2014 the light acknowledgement that does not need a written reply, and the thing to reach for when someone says \u201cthanks\u201d and a paragraph back would be worse than a thumbs-up. A REACTION IS EXACTLY ONE EMOJI: that is Bluesky\u2019s own rule, so a word or a phrase is refused here rather than by the service (where it comes back as an opaque ReactionInvalidValue). Reports the reactions Bluesky reads the message back carrying, not the one requested. Free. 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 react_to_bluesky_dm: 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.
react_to_bluesky_dm 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 react_to_bluesky_dm 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 react_to_bluesky_dm. 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.
react_to_bluesky_dm 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