This record as markdown: /tools/kh0pper-crow/crow-react.md
What crow_react does on Crow
AI agents use crow_react 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.
Why crow_react is rated Medium
Sending a reaction is a reversible write operation that creates a new record in the system. It has minimal blast radius—at worst, unwanted emoji reactions could clutter a contact's message thread, but this causes no data loss, financial impact, or unauthorized access. It does not execute arbitrary code, delete data, or move funds.
From the tool's definition Tool sends an emoji reaction, which creates/modifies data (a reaction record) in the Crow system. The description states 'Send an emoji reaction,' indicating a write action that creates new reaction data.
Attacks that exploit this kind of access
The rule that runs crow_react safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For crow_react, this is the rule to start with:
crow_react 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every crow_react call is checked against it from then on.
Questions about crow_react
Send an emoji reaction to a Crow contact. 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 crow_react: 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.
crow_react 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 crow_react 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 crow_react. 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.
crow_react 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.
More on Crow, and thousands of servers like it.
This server
Across the catalogue