Send a custom action to a Bond device.
AI agents invoke send_custom_action to trigger actions in Bond MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool sends arbitrary custom actions to Bond Bridge devices (fans, shades, lights, RF-controlled devices). Since the action is 'custom' and unspecified, it can trigger a wide range of physical device operations beyond the predefined controls available in sibling tools.
From the tool's definition 'Send a custom action to a Bond device' — executes arbitrary/custom commands on physical smart home devices
Attacks that exploit this kind of access
Send a custom action to a Bond device. It is categorised as a Execute tool in the Bond MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Bond MCP Server MCP server in PolicyLayer and add a rule for send_custom_action: 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 Bond MCP Server. Nothing to install.
send_custom_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the send_custom_action 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 send_custom_action. 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.
send_custom_action is provided by the Bond MCP Server MCP server (madorn/bond-mcp-server). 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 →