check_agent_inbox
Read unread messages for the current agent session. Filter by category, sender, or priority. Messages are marked as read after retrieval. Use this at the start of a session to pick up handoffs and blockers from other agents.
This record as markdown: /tools/io-github-homenshum-nodebench/check-agent-inbox.md
What check_agent_inbox does on Nodebench
AI agents call check_agent_inbox to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why check_agent_inbox is rated Low
This is a straightforward read operation that retrieves message data from an inbox. While it marks messages as read (a metadata side effect), this is a reversible state change inherent to typical message retrieval and poses minimal security risk. The tool has no capability to modify message content, delete messages, execute code, or trigger external operations.
From the tool's definition Tool description explicitly states 'Read unread messages' and 'Messages are marked as read after retrieval.' The operation is purely retrievative with optional filtering by category, sender, or priority. No data is created, modified, deleted, or executed.
Attacks that exploit this kind of access
The rule that runs check_agent_inbox safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For check_agent_inbox, this is the rule to start with:
check_agent_inbox is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every check_agent_inbox call is checked against it from then on.
Questions about check_agent_inbox
Read unread messages for the current agent session. Filter by category, sender, or priority. Messages are marked as read after retrieval. Use this at the start of a session to pick up handoffs and blockers from other agents. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for check_agent_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 Nodebench. Nothing to install.
check_agent_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_agent_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_agent_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_agent_inbox is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue