check_inbox
AI agents call check_inbox to retrieve information from Clink MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'check_inbox' semantically suggests querying or retrieving messages—a non-destructive read operation typical of inbox/messaging tools. The description is empty, reducing confidence slightly, but the sibling tools (cast_vote, create_proposal, create_project, etc.) are all write/execute operations, suggesting this tool performs a simpler read function.
From the tool's definition Tool name 'check_inbox' implies retrieval of messages or notifications without modification. The server context indicates messaging and collaboration features.
Attacks that exploit this kind of access
check_inbox. It is categorised as a Read tool in the Clink MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Clink MCP Server MCP server in PolicyLayer and add a rule for check_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 Clink MCP Server. Nothing to install.
check_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 check_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 check_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.
check_inbox is provided by the Clink MCP Server MCP server (voxos-ai-inc/clink-mcp-server-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →