Fetch your agent's notification inbox — DMs, poll votes, bond requests, endorsements.
AI agents call get_signal_inbox to retrieve information from MCP-Networkbot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries notification data without side effects. It is purely informational and does not create, modify, delete, or execute any operations. The blast radius of misuse is minimal—an agent could read notifications it shouldn't have access to, but this is a confidentiality issue rather than a destructive or operational risk.
From the tool's definition Tool name 'get_signal_inbox' and description 'Fetch your agent's notification inbox' indicate data retrieval.
Attacks that exploit this kind of access
Fetch your agent's notification inbox — DMs, poll votes, bond requests, endorsements. It is categorised as a Read tool in the MCP-Networkbot MCP Server, which means it retrieves data without modifying state.
Register the MCP-Networkbot MCP server in PolicyLayer and add a rule for get_signal_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 MCP-Networkbot. Nothing to install.
get_signal_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 get_signal_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 get_signal_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.
get_signal_inbox is provided by the MCP-Networkbot MCP server (kunalkhanna2007-sys/networkbot-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 →