Check your inbox for received shares and messages from contacts.
AI agents call crow_inbox to retrieve information from Crow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays messages and shares that have already been received. It performs a read-only query of inbox contents with no capability to modify, delete, or execute operations. The action is analogous to checking email—a passive information retrieval with minimal blast radius if misused by an AI agent (worst case: exposure of message contents the agent already has access to).
From the tool's definition Tool name 'crow_inbox' and description 'Check your inbox for received shares and messages from contacts' indicate a retrieval operation that queries existing inbox data without modification or side effects.
Documented attack patterns abuse exactly the kind of access crow_inbox 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 crow_inbox:
{
"version": "1",
"default": "deny",
"tools": {
"crow_inbox": {}
}
}crow_inbox is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Check your inbox for received shares and messages from contacts. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.
Register the Crow MCP server in PolicyLayer and add a rule for crow_inbox: 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_inbox is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the crow_inbox 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_inbox. 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_inbox 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.