Call the getReplyQueue MCP tool
List the LinkedIn reply drafts the reply agent flagged for human review in this workspace, newest first. Each row carries reply_job_id (pass to getDraft for the full context), the lead, the campaign, a short draft preview, confidence (0-100, clamped) and the flag reasons; on surfaces that render cards each row also carries an artifact_id. Use for "what drafts need my approval", "is the agent flagging anything", "show me what is waiting". Approving, editing or rejecting a draft (which sends or cancels a real LinkedIn message) happens only in the Reachium inbox, never through a tool.
Called through the Actions bridge: the response is that tool's own result, wrapped as { data: <tool result> } under HTTP 200. Billing, daily-cap, and confirm-step outcomes are embedded INSIDE data, never remapped to an HTTP status (see the templated /api/v1/actions/{toolName} operation above for the full protocol, and x-mcp-actions for this tool's machine-readable scope/cap/confirm_behavior fields). Authentication, request-shape, and optional idempotency-protocol failures still use their documented non-200 statuses.
Request
- Base URL: https://app.reachium.io
- URL: https://app.reachium.io/api/v1/actions/getReplyQueue
- Auth: HTTP bearer
Headers
Optional caller-generated key (8-200 characters: letters, digits, dot, underscore, colon, or hyphen). A final tool result is replayed for the same key and body. An ambiguous result remains 409 under that key; reconcile external state before using a new key. Reuse with a different body returns 422.
Request body
Response
The result of calling this tool.
Changes
No recorded changes to this operation across all 1 revision of this API.