MCP · stdio · 16 tools · 8 prompts · published
MCP server for your
AI inbox.
One npx command. Sixteen tools, eight prompts. Claude Code, Cursor, Windsurf, Zed, and Claude Desktop all get to your Instagram DMs, WhatsApp chats, template lifecycle, and delivery debugging. Free on every plan.
claude_desktop_config.json
{
"mcpServers": {
"instantreply": {
"command": "npx",
"args": [
"-y",
"@instantreply/mcp"
],
"env": {
"INSTANTREPLY_API_KEY": "ir_live_YOUR_KEY_HERE"
}
}
}
}Add the block, restart the client, ask Claude to summarize the busiest conversation today.
Install · 30 seconds
Plug it in.
- 01
Generate a key
Settings → API Keys → New. Live for production, test for sandboxed agents.
bash open https://www.instantreply.co/dashboard/settings/api-keys - 02
Add the server
Drop one block in the client config. No global install required.
json "instantreply": { "command": "npx", "args": ["-y", "@instantreply/mcp"], "env": { "INSTANTREPLY_API_KEY": "ir_live_..." } } - 03
Restart, ask
Quit and reopen the client. Ask in plain English.
text "Find unanswered DMs from today, draft a reply for each, send only after I confirm."
Tools · 16
Annotated for safe agents.
Every tool advertises readOnlyHint and destructiveHint. Compliant agents ask before they write.
list_conversationslist inbox conversationsreadget_conversationfetch one conversation with last messagereadlist_messagespaginate messages in a conversationreadsend_messagedeliver an outbound replywriteassign_conversationroute to a teammatewriteclose_conversationmark resolveddestructivelist_contactsfetch contacts and lead stagereadget_contactfetch one contactreadupdate_contactpatch name, email, lead stagewritelist_channelslist connected platformsreadget_analytics_summarydashboard stats by date rangereadget_usageAPI usage and tier headroomreadvalidate_templatecheck category fit and UTILITY coachingreadsubmit_templatesubmit a template to Meta for approvalwriteexplain_delivery_failureplain-English explanation of a failed sendreadget_developer_onboardingintegration checklist — what is done, what is nextread
Prompts · 8
Templates for the work you already do.
- /draft_reply
- Draft an answer in the team voice from the last three replies.
- /summarize_conversation
- Three sentences. Customer goal, current state, what unblocks them.
- /find_urgent_unanswered
- Rank open conversations by likelihood of churn.
- /weekly_inbox_digest
- Wins, regressions, response-time deltas. Paste-ready.
- /suggest_macros
- Surface repeated answers worth turning into canned replies.
- /escalation_note
- Internal handoff note. Risk first, context second.
- /audit_template_cost
- Check every pending template — flag MARKETING phrases, estimate savings if reworded as UTILITY.
- /debug_last_failure
- Explain the last delivery failure in plain English and suggest the next step.
Clients
Drop the block. Pick your editor.
- Claude Code
~/.claude/mcp.jsonSetup guide → - Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.jsonSetup guide → - Cursor
~/.cursor/mcp_servers.jsonSetup guide → - Windsurf
~/.codeium/windsurf/mcp_config.jsonSetup guide → - Zed
Zed → Settings → Assistant → Context ServersSetup guide → - ChatGPT
Custom GPT → Actions → Import OpenAPISetup guide → - Any MCP host
stdio transport · npm i -g @instantreply/mcp
WhatsApp workflows · conversational
Ask instead of clicking.
The MCP server exposes the same template-lifecycle and delivery-debug APIs as conversational tools. You can drive the full workflow — validate, reword, submit, debug — without opening Meta Business Manager or reading error codes.
- Template UTILITY coaching
- Ask: "Check my pending templates and tell me which ones qualify as UTILITY." The validate_template tool returns flagged marketing phrases and estimated savings. UTILITY templates cost ~66% less than MARKETING.
- Submit to Meta
- Once the coaching is clear, ask: "Fix the flagged phrases and submit." The submit_template tool routes the corrected template to Meta and returns the approval status.
- Explain a delivery failure
- Ask: "Why did the last campaign message fail for contact X?" The explain_delivery_failure tool returns what happened, whether the fault is ours or Meta's, and whether a retry is safe.
- Developer onboarding checklist
- Ask: "What integration steps are still incomplete?" The get_developer_onboarding tool returns a checklist of which steps are done and which are not — connect channel, validate first template, register webhook.
Permissions · scopes
The key controls what the agent can do.
Every MCP tool maps to an API key scope. Read tools require conversations:read. Write tools require messages:send. Template tools require templates:write to validate and templates:submit to submit.
Use a read-only key for agent sessions that should only observe. Use a full-scope key for agents that send messages or submit templates. Both key types work with the same server config — just swap the key value.
Every tool advertises readOnlyHint and destructiveHint so compliant MCP clients ask for confirmation before any write action.
# Read-only agent: observe and debug
IR_API_KEY=ir_live_... # scopes: conversations:read
# Full agent: validate, submit, send
IR_API_KEY=ir_live_... # scopes: conversations:read,
# messages:send,
# templates:write,
# templates:submitThe model is ready. The tools are wired.