Send iMessages from Claude

What does your team get when Claude can operate the line?#

The gap was never writing. It's availability checks, personalization, manual pasting. With the MCP server, point Claude at a CSV and it handles the rest: drafting and tracking.

• Blue bubbles with read receipts and typing indicators use the same thread colleagues and family do. This looks like a person, not a platform, so customers book 2-3x more appointments where a booking funnel exists.
• Dedicated line, unlimited iMessages with RCS then SMS fallback. Pace: 50 opted-in / 30 cold new contacts daily; replies never metered. No A2P registration or brand vetting required.

How do you connect Claude to Blue Reacher?#

The server is hosted at https://api.bluereacher.com/v1/mcp over Streamable HTTP: nothing to install, no Node. You need an API key from your dashboard; keep it in MCP config or a secrets manager, never in a prompt.

• White-glove setup handles it: dedicated line, message intent tuning, MCP server wiring. Docs at docs.bluereacher.com cover schemas, shapes, rate limits, error codes.

• Claude Code, one command: claude mcp add --transport http bluereacher https://api.bluereacher.com/v1/mcp --header "Authorization: Bearer brk_live_your_key"
• Confirm it connected by running claude mcp list, which shows the server and its tool count
• Claude Desktop and Cursor (.cursor/mcp.json), paste: {"mcpServers": {"bluereacher": {"type": "http", "url": "https://api.bluereacher.com/v1/mcp", "headers": {"Authorization": "Bearer brk_live_your_key"}}}}
• Restart the client after saving. The tools appear under a bluereacher group
• Rotating the key in your dashboard takes effect on the next tool call, and a bad key returns a clear 401 instead of failing quietly

What does an operator actually type?#

The prompts below are what a sales manager types, not code. The pattern that holds up in practice: ask for the read first, approve what comes back, then ask for the send.

• "Check whether +1 415 555 0198 can receive iMessage. Report the answer, do not send anything."
• "Read trials.csv, check iMessage availability for all 12 numbers, then draft one message per person referencing their company. Show me the drafts. Do not send."
• "Send the three drafts I just approved from line_9f2c1a, one at a time, and report each status."
• "Pull the last 50 messages on that line and summarize every reply that mentions pricing."
• "The message to +1 415 555 0198 went out this morning. Did it deliver?"
• "Show me every message from the last hour with status failed, with the recipient number for each."
• "List my active lines and tell me which one is labeled for West Coast."

Where does a human have to stay in the loop?#

Blue Reacher's send_message tool is the one that touches a real person. Treat it differently from readers like lookup_imessage and get_conversation: reading is convenient, sending unattended is a liability.

• Consent, quiet hours, and pacing still apply; STOP opt-outs auto-detected. No A2P registration doesn't mean permission to text strangers; point Claude at defensible lists and pace like a person would.

• Rehearse on a brk_test_ sandbox key first. Every tool answers with realistic simulated data and nothing real is sent, so the whole workflow runs before a live key is in play
• Scope the key. Issue one key per agent, bound to one workspace with read or write permission, so one revoke kills it without touching your production integration
• Require approval on sends. In Claude Code, keep send_message off the auto-approve list so every call surfaces a confirmation
• Keep a human on bulk work. Have Claude draft and show the full batch, then send only after you approve it. One message per call, no unattended loops
• Log the returned message id on every send so each message ties back to the record that triggered it
• Watch the activity feed. Every tool call lands in your dashboard with the key that made it