get_push_response
Read back a device's answer to an actionable push (#75) by the correlation_id returned from send_push. Returns the push_responses row { correlation_id, device_uuid, action (accept|reject|skip), context, responded_at, action_intent } or null if the user hasn't responded yet. action_intent (or null...
This record as markdown: /tools/dev-busymate-busymate-devtools/get-push-response.md
What get_push_response does on Busymate DevTools
AI agents call get_push_response to retrieve information from Busymate DevTools without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
correlation_id | string | Yes | The correlation_id returned by send_push when actionable:true. |
Parameters from the server's own tool schema.
Why get_push_response is rated Low
This tool retrieves and inspects data (push notification responses and their outcomes) without creating, modifying, deleting, or executing any operations. The mention of 'action_intent' showing what 'the binding actually did' refers to historical information about past actions, not new execution initiated by this tool.
From the tool's definition Tool name and description establish read-only retrieval: 'Read back a device's answer', 'Returns the push_responses row...or null if the user hasn't responded yet'.
Attacks that exploit this kind of access
The rule that runs get_push_response safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Busymate DevTools, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_push_response, this is the rule to start with:
get_push_response 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 Busymate DevTools, apply this rule, and every get_push_response call is checked against it from then on.
Questions about get_push_response
Read back a device's answer to an actionable push (#75) by the correlation_id returned from send_push. Returns the push_responses row { correlation_id, device_uuid, action (accept|reject|skip), context, responded_at, action_intent } or null if the user hasn't responded yet. action_intent (or null) carries the SERVER-RECORDED action-binding + its outcome: { action_kind, params, issued_by, created_at, executed_at, result } — so you learn BOTH the user's choice and what the binding actually did (e.g. block_rule_toggle result.enabled_after). It is categorised as a Read tool in the Busymate DevTools MCP Server, which means it retrieves data without modifying state.
get_push_response accepts 1 parameter: correlation_id. Required: correlation_id. The full parameter table on this page comes from the server's own tool schema.
Register the Busymate DevTools MCP server in PolicyLayer and add a rule for get_push_response: 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 Busymate DevTools. Nothing to install.
get_push_response 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_push_response 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_push_response. 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_push_response is provided by the Busymate DevTools MCP server (https://mcp.busymate.dev). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Busymate DevTools, and thousands of servers like it.
This server
Across the catalogue